mirror of
https://github.com/codewhale-hq/Codewhale.git
synced 2026-11-07 10:36:05 -10:00
Hunter BandCopilot App
881f31c3cd
Add stable tencent/hy4 to the OpenRouter catalog with reviewed limits and aliases, and a Tencent TokenHub compatible descriptor using hy4 and TENCENT_API_KEY. Direct TokenHub pricing remains explicitly unknown rather than inheriting OpenRouter rates. Replace the duplicated OpenRouter alias match with the reviewed compatibility table (102 existing aliases verified unchanged). Catalog relock also carries upstream models.dev price and metadata updates. Validation: focused config/engine/tui nextest 559 run, 557 passed before updating two stale count fixtures, which then passed with feature_registry (4/4); catalog script tests 18 OK; render --check, provider registry, preflight, fmt passed; web vitest 771/771. No paid Tencent call was made. Co-authored-by: Copilot App <[email protected]>
6488 lines
166 KiB
JSON
6488 lines
166 KiB
JSON
{
|
|
"source": {
|
|
"url": "https://models.dev/catalog.json",
|
|
"fetched_at": "2026-11-06T04:39:42Z",
|
|
"sha256": "83270dc8406a2bc8ab486a5fcce9fb208bd6de19792c90bcb0cca2223a2a57ec"
|
|
},
|
|
"models": {
|
|
"deepseek/deepseek-v4-pro-0813": {
|
|
"id": "deepseek/deepseek-v4-pro-0813",
|
|
"name": "DeepSeek V4 Pro 0813",
|
|
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
|
|
"family": "deepseek-thinking",
|
|
"release_date": "2026-08-13",
|
|
"last_updated": "2026-08-22",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"license": "MIT",
|
|
"weights": [
|
|
{
|
|
"label": "Hugging Face",
|
|
"url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
}
|
|
],
|
|
"benchmarks": [
|
|
{
|
|
"name": "Humanity's Last Exam",
|
|
"score": 42.7,
|
|
"metric": "score",
|
|
"variant": "without tools",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "Humanity's Last Exam",
|
|
"score": 60,
|
|
"metric": "score",
|
|
"variant": "with tools",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 87.9,
|
|
"metric": "score",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "max effort",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "NL2Repo",
|
|
"score": 61.5,
|
|
"metric": "score",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "max effort",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "CyberGym",
|
|
"score": 83.3,
|
|
"metric": "score",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "max effort",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 62.7,
|
|
"metric": "score",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "max effort",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "Toolathlon-Verified",
|
|
"score": 74.1,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "Agents' Last Exam",
|
|
"score": 25.7,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "AutomationBench",
|
|
"score": 31.8,
|
|
"metric": "score",
|
|
"dataset": "public",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "DSBench-FullStack",
|
|
"score": 71.1,
|
|
"metric": "score",
|
|
"dataset": "internal",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
},
|
|
{
|
|
"name": "DSBench-Hard",
|
|
"score": 67.2,
|
|
"metric": "score",
|
|
"dataset": "internal",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"
|
|
}
|
|
]
|
|
},
|
|
"deepseek/deepseek-v4.1-flash": {
|
|
"id": "deepseek/deepseek-v4.1-flash",
|
|
"name": "DeepSeek V4.1 Flash",
|
|
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-09-10",
|
|
"last_updated": "2026-09-10",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"license": "MIT",
|
|
"weights": [
|
|
{
|
|
"label": "Hugging Face",
|
|
"url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
}
|
|
],
|
|
"benchmarks": [
|
|
{
|
|
"name": "GPQA Diamond",
|
|
"score": 90.9,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "MathArena Apex",
|
|
"score": 65.6,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Humanity's Last Exam",
|
|
"score": 36.8,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"dataset": "full set",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Humanity's Last Exam",
|
|
"score": 39.1,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"dataset": "text-only subset",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Codeforces",
|
|
"score": 3471,
|
|
"metric": "rating",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 90.6,
|
|
"metric": "pass@1",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 30,
|
|
"metric": "pass@1",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "3.0",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 31.2,
|
|
"metric": "pass@1",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "4.0",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 74.2,
|
|
"metric": "resolved",
|
|
"harness": "mini-swe-agent",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "ProgramBench",
|
|
"score": 20.3,
|
|
"metric": "almost@1",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "NL2Repo",
|
|
"score": 64,
|
|
"metric": "score",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "CyberGym",
|
|
"score": 88.1,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "ExploitGym",
|
|
"score": 15.3,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "AutomationBench",
|
|
"score": 54.8,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Agents' Last Exam",
|
|
"score": 31.8,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "SEC-Bench Pro",
|
|
"score": 62.8,
|
|
"metric": "pass@1",
|
|
"harness": "Claude Code",
|
|
"variant": "reasoning_effort=100",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Humanity's Last Exam",
|
|
"score": 63.9,
|
|
"metric": "pass@1",
|
|
"variant": "reasoning_effort=100; with tools",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Chartography",
|
|
"score": 78.9,
|
|
"metric": "pass@1",
|
|
"harness": "Claude Code",
|
|
"variant": "reasoning_effort=100; with tools",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "BabyVision",
|
|
"score": 89.6,
|
|
"metric": "pass@1",
|
|
"harness": "Claude Code",
|
|
"variant": "reasoning_effort=100; with tools",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "ZeroBench",
|
|
"score": 49,
|
|
"metric": "pass@5",
|
|
"harness": "Claude Code",
|
|
"variant": "reasoning_effort=100; with tools",
|
|
"dataset": "main",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 69.8,
|
|
"metric": "resolved",
|
|
"harness": "Claude Code",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 88,
|
|
"metric": "pass@1",
|
|
"harness": "Claude Code",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 65.6,
|
|
"metric": "resolved",
|
|
"harness": "Codex",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 84.1,
|
|
"metric": "pass@1",
|
|
"harness": "Codex",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 65.5,
|
|
"metric": "resolved",
|
|
"harness": "OpenCode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 85,
|
|
"metric": "pass@1",
|
|
"harness": "OpenCode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 66.2,
|
|
"metric": "resolved",
|
|
"harness": "Pi",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 86.1,
|
|
"metric": "pass@1",
|
|
"harness": "Pi",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 90.3,
|
|
"metric": "pass@1",
|
|
"harness": "mini-swe-agent",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 72.6,
|
|
"metric": "resolved",
|
|
"harness": "DeepSeek Harness minimal mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 70.5,
|
|
"metric": "resolved",
|
|
"harness": "DeepSeek Harness standard mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 85.8,
|
|
"metric": "pass@1",
|
|
"harness": "DeepSeek Harness standard mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 67.6,
|
|
"metric": "resolved",
|
|
"harness": "DeepSeek Harness PTC mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 85.8,
|
|
"metric": "pass@1",
|
|
"harness": "DeepSeek Harness PTC mode",
|
|
"variant": "reasoning_effort=100",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
|
|
}
|
|
]
|
|
},
|
|
"xiaomi/mimo-v2.6-flash": {
|
|
"id": "xiaomi/mimo-v2.6-flash",
|
|
"name": "MiMo-V2.6-Flash",
|
|
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
|
|
"family": "mimo",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"audio",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"weights": [
|
|
{
|
|
"label": "Hugging Face",
|
|
"url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
}
|
|
],
|
|
"benchmarks": [
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 67.9,
|
|
"metric": "score",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "ProgramBench",
|
|
"score": 26,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "MiMo Code Bench",
|
|
"score": 61.2,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "AutomationBench",
|
|
"score": 52.3,
|
|
"metric": "score",
|
|
"version": "1.0.6",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Toolathlon-Verified",
|
|
"score": 73.6,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Agents' Last Exam",
|
|
"score": 27.6,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 28.8,
|
|
"metric": "score",
|
|
"version": "4.0",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 87.6,
|
|
"metric": "score",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "OSWorld-Verified",
|
|
"score": 80.8,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "JobBench",
|
|
"score": 61.2,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "CyberGym",
|
|
"score": 95.1,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "MiMo Cyber Bench",
|
|
"score": 77.2,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "ExploitGym",
|
|
"score": 6,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "ExploitBench",
|
|
"score": 25.3,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "SEC-Bench Pro",
|
|
"score": 47.5,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "MiMo VisualCoding",
|
|
"score": 71.5,
|
|
"metric": "score",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
}
|
|
]
|
|
},
|
|
"xiaomi/mimo-v2.6-pro": {
|
|
"id": "xiaomi/mimo-v2.6-pro",
|
|
"name": "MiMo-V2.6-Pro",
|
|
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
|
|
"family": "mimo",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"audio",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"weights": [
|
|
{
|
|
"label": "Hugging Face",
|
|
"url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"
|
|
}
|
|
],
|
|
"benchmarks": [
|
|
{
|
|
"name": "DeepSWE",
|
|
"score": 71.9,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"version": "1.1",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "ProgramBench",
|
|
"score": 26.5,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "MiMo Code Bench",
|
|
"score": 63.2,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "AutomationBench",
|
|
"score": 53.1,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"version": "1.0.6",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Toolathlon-Verified",
|
|
"score": 76.9,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "GDPval-AA",
|
|
"score": 1673,
|
|
"metric": "Elo",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Agents' Last Exam",
|
|
"score": 31.6,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 34.9,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"version": "4.0",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "Terminal-Bench",
|
|
"score": 89.9,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"version": "2.1",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "OSWorld-Verified",
|
|
"score": 82,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "JobBench",
|
|
"score": 62,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "CyberGym",
|
|
"score": 94,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "MiMo Cyber Bench",
|
|
"score": 80.2,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "ExploitGym",
|
|
"score": 17.8,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "ExploitBench",
|
|
"score": 47.9,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "SEC-Bench Pro",
|
|
"score": 66.3,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
},
|
|
{
|
|
"name": "MiMo VisualCoding",
|
|
"score": 72.3,
|
|
"metric": "score",
|
|
"variant": "MiMo-V2.6 Pro comparison column",
|
|
"source": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"providers": {
|
|
"alibaba-coding-plan": {
|
|
"qwen3.7-plus": {
|
|
"id": "qwen3.7-plus",
|
|
"canonical_model_id": "alibaba/qwen3.7-plus",
|
|
"name": "Qwen3.7 Plus",
|
|
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
|
|
"family": "qwen",
|
|
"knowledge": "2025-04",
|
|
"release_date": "2026-06-02",
|
|
"last_updated": "2026-06-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 64000
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
}
|
|
},
|
|
"alibaba-token-plan": {
|
|
"deepseek-v4-flash-0731": {
|
|
"id": "deepseek-v4-flash-0731",
|
|
"canonical_model_id": "deepseek/deepseek-v4-flash-0731",
|
|
"name": "DeepSeek V4 Flash 0731",
|
|
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-07-31",
|
|
"last_updated": "2026-07-31",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"deepseek-v4-pro": {
|
|
"id": "deepseek-v4-pro",
|
|
"canonical_model_id": "deepseek/deepseek-v4-pro",
|
|
"name": "DeepSeek V4 Pro",
|
|
"description": "Open MoE flagship with million-token context for coding and long agent runs",
|
|
"family": "deepseek-thinking",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-04-24",
|
|
"last_updated": "2026-04-24",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"glm-5.2": {
|
|
"id": "glm-5.2",
|
|
"canonical_model_id": "zhipuai/glm-5.2",
|
|
"name": "GLM-5.2",
|
|
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
|
|
"family": "glm",
|
|
"release_date": "2026-06-13",
|
|
"last_updated": "2026-06-13",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"qwen3.6-flash": {
|
|
"id": "qwen3.6-flash",
|
|
"canonical_model_id": "alibaba/qwen3.6-flash",
|
|
"name": "Qwen3.6 Flash",
|
|
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
|
|
"family": "qwen3.6",
|
|
"release_date": "2026-04-27",
|
|
"last_updated": "2026-04-27",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "budget_tokens",
|
|
"max": 131072
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"qwen3.7-max": {
|
|
"id": "qwen3.7-max",
|
|
"canonical_model_id": "alibaba/qwen3.7-max",
|
|
"name": "Qwen3.7 Max",
|
|
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
|
|
"family": "qwen",
|
|
"release_date": "2026-05-21",
|
|
"last_updated": "2026-05-21",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "budget_tokens",
|
|
"max": 262144
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"qwen3.7-plus": {
|
|
"id": "qwen3.7-plus",
|
|
"canonical_model_id": "alibaba/qwen3.7-plus",
|
|
"name": "Qwen3.7 Plus",
|
|
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
|
|
"family": "qwen",
|
|
"knowledge": "2025-04",
|
|
"release_date": "2026-06-02",
|
|
"last_updated": "2026-06-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "budget_tokens",
|
|
"max": 262144
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"qwen3.8-max": {
|
|
"id": "qwen3.8-max",
|
|
"canonical_model_id": "alibaba/qwen3.8-max",
|
|
"name": "Qwen3.8 Max",
|
|
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
|
|
"family": "qwen",
|
|
"release_date": "2026-08-03",
|
|
"last_updated": "2026-08-03",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"xhigh"
|
|
]
|
|
},
|
|
{
|
|
"type": "budget_tokens",
|
|
"min": 0,
|
|
"max": 262144
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0,
|
|
"cache_read": 0,
|
|
"cache_write": 0
|
|
}
|
|
}
|
|
},
|
|
"anthropic": {
|
|
"claude-fable-5": {
|
|
"id": "claude-fable-5",
|
|
"name": "Claude Fable 5",
|
|
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
|
|
"family": "claude-fable",
|
|
"release_date": "2026-06-07",
|
|
"last_updated": "2026-06-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 10,
|
|
"output": 50,
|
|
"cache_read": 1,
|
|
"cache_write": 12.5
|
|
}
|
|
},
|
|
"claude-fable-5-1": {
|
|
"id": "claude-fable-5-1",
|
|
"canonical_model_id": "anthropic/claude-fable-5-1",
|
|
"name": "Claude Fable 5.1",
|
|
"description": "Claude model for demanding reasoning and long-horizon agentic work",
|
|
"family": "claude-fable",
|
|
"knowledge": "2026-06",
|
|
"release_date": "2026-09-01",
|
|
"last_updated": "2026-09-01",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 10,
|
|
"output": 50,
|
|
"cache_read": 0.25,
|
|
"cache_write": 12.5
|
|
}
|
|
},
|
|
"claude-haiku-4-5": {
|
|
"id": "claude-haiku-4-5",
|
|
"canonical_model_id": "anthropic/claude-haiku-4-5",
|
|
"name": "Claude Haiku 4.5 (latest)",
|
|
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
|
|
"family": "claude-haiku",
|
|
"knowledge": "2025-02-28",
|
|
"release_date": "2025-10-15",
|
|
"last_updated": "2025-10-15",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "budget_tokens",
|
|
"min": 1024
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 200000,
|
|
"output": 64000
|
|
},
|
|
"cost": {
|
|
"input": 1,
|
|
"output": 5,
|
|
"cache_read": 0.1,
|
|
"cache_write": 1.25
|
|
}
|
|
},
|
|
"claude-haiku-5-5": {
|
|
"id": "claude-haiku-5-5",
|
|
"canonical_model_id": "anthropic/claude-haiku-5-5",
|
|
"name": "Claude Haiku 5.5",
|
|
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
|
|
"family": "claude-haiku",
|
|
"knowledge": "2026-06",
|
|
"release_date": "2026-10-07",
|
|
"last_updated": "2026-10-07",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 0.1,
|
|
"output": 0.5,
|
|
"cache_read": 0.01,
|
|
"cache_write": 0.125,
|
|
"tiers": [
|
|
{
|
|
"input": 0.5,
|
|
"output": 2.5,
|
|
"cache_read": 0.05,
|
|
"cache_write": 0.625,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 100000
|
|
}
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"claude-opus-4-8": {
|
|
"id": "claude-opus-4-8",
|
|
"name": "Claude Opus 4.8",
|
|
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
|
|
"family": "claude-opus",
|
|
"knowledge": "2026-01",
|
|
"release_date": "2026-05-28",
|
|
"last_updated": "2026-05-28",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 5,
|
|
"output": 25,
|
|
"cache_read": 0.5,
|
|
"cache_write": 6.25
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 10,
|
|
"output": 50,
|
|
"cache_read": 1,
|
|
"cache_write": 12.5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"speed": "fast"
|
|
},
|
|
"headers": {
|
|
"anthropic-beta": "fast-mode-2026-02-01"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"claude-opus-5": {
|
|
"id": "claude-opus-5",
|
|
"canonical_model_id": "anthropic/claude-opus-5",
|
|
"name": "Claude Opus 5",
|
|
"description": "Strongest Claude Opus model for coding, agents, and professional work",
|
|
"family": "claude-opus",
|
|
"knowledge": "2026-05",
|
|
"release_date": "2026-07-24",
|
|
"last_updated": "2026-07-24",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 5,
|
|
"output": 25,
|
|
"cache_read": 0.5,
|
|
"cache_write": 6.25
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 10,
|
|
"output": 50,
|
|
"cache_read": 1,
|
|
"cache_write": 12.5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"speed": "fast"
|
|
},
|
|
"headers": {
|
|
"anthropic-beta": "fast-mode-2026-02-01"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"claude-opus-5-5": {
|
|
"id": "claude-opus-5-5",
|
|
"canonical_model_id": "anthropic/claude-opus-5-5",
|
|
"name": "Claude Opus 5.5",
|
|
"description": "Claude model for long-running agentic coding and knowledge work",
|
|
"family": "claude-opus",
|
|
"knowledge": "2026-06",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.2,
|
|
"cache_write": 5
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 8,
|
|
"output": 40,
|
|
"cache_read": 0.4,
|
|
"cache_write": 10
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"speed": "fast"
|
|
},
|
|
"headers": {
|
|
"anthropic-beta": "fast-mode-2026-02-01"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"claude-sonnet-4-6": {
|
|
"id": "claude-sonnet-4-6",
|
|
"name": "Claude Sonnet 4.6",
|
|
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
|
|
"family": "claude-sonnet",
|
|
"knowledge": "2025-08-31",
|
|
"release_date": "2026-02-17",
|
|
"last_updated": "2026-03-13",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"max"
|
|
]
|
|
},
|
|
{
|
|
"type": "budget_tokens",
|
|
"min": 1024
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 3,
|
|
"output": 15,
|
|
"cache_read": 0.3,
|
|
"cache_write": 3.75
|
|
}
|
|
},
|
|
"claude-sonnet-5": {
|
|
"id": "claude-sonnet-5",
|
|
"name": "Claude Sonnet 5",
|
|
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
|
|
"family": "claude-sonnet",
|
|
"knowledge": "2026-01-31",
|
|
"release_date": "2026-06-29",
|
|
"last_updated": "2026-06-30",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.2,
|
|
"cache_write": 2.5
|
|
}
|
|
},
|
|
"claude-sonnet-5-5": {
|
|
"id": "claude-sonnet-5-5",
|
|
"canonical_model_id": "anthropic/claude-sonnet-5-5",
|
|
"name": "Claude Sonnet 5.5",
|
|
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
|
|
"family": "claude-sonnet",
|
|
"knowledge": "2026-06",
|
|
"release_date": "2026-09-28",
|
|
"last_updated": "2026-09-28",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.1,
|
|
"cache_write": 2.5
|
|
}
|
|
}
|
|
},
|
|
"arcee": {
|
|
"trinity-large-thinking": {
|
|
"id": "trinity-large-thinking",
|
|
"canonical_model_id": "arcee-ai/trinity-large-thinking",
|
|
"name": "Trinity Large Thinking",
|
|
"description": "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use",
|
|
"family": "trinity",
|
|
"release_date": "2026-04-01",
|
|
"last_updated": "2026-05-28",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 80000
|
|
},
|
|
"cost": {
|
|
"input": 0.25,
|
|
"output": 0.8,
|
|
"cache_read": 0.06
|
|
},
|
|
"status": "beta"
|
|
}
|
|
},
|
|
"deepseek": {
|
|
"deepseek-flash": {
|
|
"id": "deepseek-flash",
|
|
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
|
|
"name": "DeepSeek V4.1 Flash 1017",
|
|
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-10-17",
|
|
"last_updated": "2026-10-17",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 393216
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.6,
|
|
"cache_read": 0.003,
|
|
"reasoning": 0.6
|
|
}
|
|
},
|
|
"deepseek-v4-flash": {
|
|
"id": "deepseek-v4-flash",
|
|
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
|
|
"name": "DeepSeek V4 Flash",
|
|
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-10-17",
|
|
"last_updated": "2026-10-17",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 393216
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.6,
|
|
"cache_read": 0.003,
|
|
"reasoning": 0.6
|
|
},
|
|
"status": "deprecated"
|
|
},
|
|
"deepseek-v4-flash-vision-exp": {
|
|
"id": "deepseek-v4-flash-vision-exp",
|
|
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
|
|
"name": "DeepSeek V4 Flash Vision Exp",
|
|
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-10-17",
|
|
"last_updated": "2026-10-17",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 393216
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.6,
|
|
"cache_read": 0.003,
|
|
"reasoning": 0.6
|
|
},
|
|
"status": "deprecated"
|
|
},
|
|
"deepseek-v4-pro": {
|
|
"id": "deepseek-v4-pro",
|
|
"canonical_model_id": "deepseek/deepseek-v4-pro-0813",
|
|
"name": "DeepSeek V4 Pro",
|
|
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
|
|
"family": "deepseek-thinking",
|
|
"release_date": "2026-08-13",
|
|
"last_updated": "2026-08-22",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 393216
|
|
},
|
|
"cost": {
|
|
"input": 0.66,
|
|
"output": 1.98,
|
|
"cache_read": 0.022,
|
|
"reasoning": 1.98
|
|
}
|
|
}
|
|
},
|
|
"google": {
|
|
"gemini-3.1-flash-lite": {
|
|
"id": "gemini-3.1-flash-lite",
|
|
"name": "Gemini 3.1 Flash Lite",
|
|
"description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
|
|
"family": "gemini-flash-lite",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-05-07",
|
|
"last_updated": "2026-05-07",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.25,
|
|
"output": 1.5,
|
|
"cache_read": 0.025,
|
|
"input_audio": 0.5
|
|
}
|
|
},
|
|
"gemini-3.1-pro-preview": {
|
|
"id": "gemini-3.1-pro-preview",
|
|
"name": "Gemini 3.1 Pro Preview",
|
|
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
|
|
"family": "gemini-pro",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-02-19",
|
|
"last_updated": "2026-02-19",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 12,
|
|
"cache_read": 0.2,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 18,
|
|
"cache_read": 0.4,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 200000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 18,
|
|
"cache_read": 0.4
|
|
}
|
|
}
|
|
},
|
|
"gemini-3.5-flash": {
|
|
"id": "gemini-3.5-flash",
|
|
"name": "Gemini 3.5 Flash",
|
|
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
|
|
"family": "gemini-flash",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-05-19",
|
|
"last_updated": "2026-05-19",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 1.5,
|
|
"output": 9,
|
|
"cache_read": 0.15,
|
|
"input_audio": 1.5
|
|
}
|
|
},
|
|
"gemini-3.5-flash-lite": {
|
|
"id": "gemini-3.5-flash-lite",
|
|
"canonical_model_id": "google/gemini-3.5-flash-lite",
|
|
"name": "Gemini 3.5 Flash Lite",
|
|
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
|
|
"family": "gemini-flash-lite",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-07-21",
|
|
"last_updated": "2026-07-21",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.3,
|
|
"output": 2.5,
|
|
"cache_read": 0.03
|
|
}
|
|
},
|
|
"gemini-3.6-flash": {
|
|
"id": "gemini-3.6-flash",
|
|
"canonical_model_id": "google/gemini-3.6-flash",
|
|
"name": "Gemini 3.6 Flash",
|
|
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
|
|
"family": "gemini-flash",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-07-21",
|
|
"last_updated": "2026-07-21",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.75,
|
|
"output": 3.75,
|
|
"cache_read": 0.075,
|
|
"input_audio": 0.75
|
|
}
|
|
},
|
|
"gemini-3.7-flash": {
|
|
"id": "gemini-3.7-flash",
|
|
"canonical_model_id": "google/gemini-3.7-flash",
|
|
"name": "Gemini 3.7 Flash",
|
|
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
|
|
"family": "gemini-flash",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-08-13",
|
|
"last_updated": "2026-08-13",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.75,
|
|
"output": 3.75,
|
|
"cache_read": 0.075,
|
|
"input_audio": 0.75
|
|
}
|
|
},
|
|
"gemini-3.8-flash": {
|
|
"id": "gemini-3.8-flash",
|
|
"canonical_model_id": "google/gemini-3.8-flash",
|
|
"name": "Gemini 3.8 Flash",
|
|
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
|
|
"family": "gemini-flash",
|
|
"release_date": "2026-09-02",
|
|
"last_updated": "2026-09-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.75,
|
|
"output": 3.75,
|
|
"cache_read": 0.075,
|
|
"input_audio": 0.75
|
|
}
|
|
},
|
|
"gemini-4-argon": {
|
|
"id": "gemini-4-argon",
|
|
"canonical_model_id": "google/gemini-4-argon",
|
|
"name": "Gemini 4 Argon",
|
|
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
|
|
"family": "gemini",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-10-13",
|
|
"last_updated": "2026-10-13",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 32768
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.1,
|
|
"input_audio": 2
|
|
}
|
|
},
|
|
"gemini-flash-latest": {
|
|
"id": "gemini-flash-latest",
|
|
"name": "Gemini Flash Latest",
|
|
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
|
|
"family": "gemini-flash",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-08-13",
|
|
"last_updated": "2026-08-13",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.75,
|
|
"output": 3.75,
|
|
"cache_read": 0.075,
|
|
"input_audio": 0.75
|
|
}
|
|
},
|
|
"gemini-flash-lite-latest": {
|
|
"id": "gemini-flash-lite-latest",
|
|
"name": "Gemini Flash-Lite Latest",
|
|
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
|
|
"family": "gemini-flash-lite",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-07-21",
|
|
"last_updated": "2026-07-21",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.3,
|
|
"output": 2.5,
|
|
"cache_read": 0.03
|
|
}
|
|
},
|
|
"gemma-4-26b-a4b-it": {
|
|
"id": "gemma-4-26b-a4b-it",
|
|
"name": "Gemma 4 26B A4B IT",
|
|
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
|
|
"family": "gemma",
|
|
"release_date": "2026-04-02",
|
|
"last_updated": "2026-04-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 32768
|
|
}
|
|
},
|
|
"gemma-4-31b-it": {
|
|
"id": "gemma-4-31b-it",
|
|
"name": "Gemma 4 31B IT",
|
|
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
|
|
"family": "gemma",
|
|
"release_date": "2026-04-02",
|
|
"last_updated": "2026-04-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 32768
|
|
}
|
|
}
|
|
},
|
|
"meta": {
|
|
"muse-spark-1.1": {
|
|
"id": "muse-spark-1.1",
|
|
"canonical_model_id": "meta/muse-spark-1.1",
|
|
"name": "Muse Spark 1.1",
|
|
"description": "Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.",
|
|
"family": "muse",
|
|
"release_date": "2026-04-08",
|
|
"last_updated": "2026-07-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.25,
|
|
"output": 4.25,
|
|
"cache_read": 0.15
|
|
}
|
|
},
|
|
"muse-spark-1.2": {
|
|
"id": "muse-spark-1.2",
|
|
"canonical_model_id": "meta/muse-spark-1.2",
|
|
"name": "Muse Spark 1.2",
|
|
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
|
|
"family": "muse",
|
|
"release_date": "2026-08-05",
|
|
"last_updated": "2026-08-05",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf",
|
|
"audio"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.25,
|
|
"output": 4.25,
|
|
"cache_read": 0.15
|
|
}
|
|
},
|
|
"muse-spark-1.2-contributor": {
|
|
"id": "muse-spark-1.2-contributor",
|
|
"canonical_model_id": "meta/muse-spark-1.2",
|
|
"name": "Muse Spark 1.2 Contributor",
|
|
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
|
|
"family": "muse",
|
|
"release_date": "2026-08-05",
|
|
"last_updated": "2026-08-05",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf",
|
|
"audio"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.1,
|
|
"output": 0.2,
|
|
"cache_read": 0.002
|
|
}
|
|
},
|
|
"muse-spark-1.3": {
|
|
"id": "muse-spark-1.3",
|
|
"canonical_model_id": "meta/muse-spark-1.3",
|
|
"name": "Muse Spark 1.3",
|
|
"description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.",
|
|
"family": "muse",
|
|
"release_date": "2026-09-02",
|
|
"last_updated": "2026-09-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf",
|
|
"audio"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.25,
|
|
"output": 4.25,
|
|
"cache_read": 0.15
|
|
}
|
|
},
|
|
"muse-spark-1.3-contributor": {
|
|
"id": "muse-spark-1.3-contributor",
|
|
"canonical_model_id": "meta/muse-spark-1.3",
|
|
"name": "Muse Spark 1.3 Contributor",
|
|
"description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.",
|
|
"family": "muse",
|
|
"release_date": "2026-09-02",
|
|
"last_updated": "2026-09-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf",
|
|
"audio"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.1,
|
|
"output": 0.2,
|
|
"cache_read": 0.002
|
|
}
|
|
},
|
|
"muse-wonder-1.0": {
|
|
"id": "muse-wonder-1.0",
|
|
"canonical_model_id": "meta/muse-wonder-1.0",
|
|
"name": "Muse Wonder",
|
|
"description": "Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.",
|
|
"family": "muse",
|
|
"release_date": "2026-10-12",
|
|
"last_updated": "2026-10-12",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf",
|
|
"audio"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.2
|
|
}
|
|
}
|
|
},
|
|
"minimax": {
|
|
"MiniMax-M2.7": {
|
|
"id": "MiniMax-M2.7",
|
|
"name": "MiniMax-M2.7",
|
|
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
|
|
"family": "minimax",
|
|
"release_date": "2026-03-18",
|
|
"last_updated": "2026-03-18",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [],
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 204800,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.3,
|
|
"output": 1.2,
|
|
"cache_read": 0.06,
|
|
"cache_write": 0.375
|
|
},
|
|
"status": "deprecated"
|
|
},
|
|
"MiniMax-M2.7-highspeed": {
|
|
"id": "MiniMax-M2.7-highspeed",
|
|
"name": "MiniMax-M2.7-highspeed",
|
|
"description": "Low-latency M2.7 variant for interactive coding plans and agent loops",
|
|
"family": "minimax",
|
|
"release_date": "2026-03-18",
|
|
"last_updated": "2026-03-18",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [],
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 204800,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.6,
|
|
"output": 2.4,
|
|
"cache_read": 0.06,
|
|
"cache_write": 0.375
|
|
},
|
|
"status": "deprecated"
|
|
},
|
|
"MiniMax-M3": {
|
|
"id": "MiniMax-M3",
|
|
"name": "MiniMax-M3",
|
|
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
|
|
"family": "minimax",
|
|
"release_date": "2026-06-01",
|
|
"last_updated": "2026-06-25",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": false,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 524288
|
|
},
|
|
"cost": {
|
|
"input": 0.3,
|
|
"output": 1.2,
|
|
"cache_read": 0.06,
|
|
"tiers": [
|
|
{
|
|
"input": 0.6,
|
|
"output": 2.4,
|
|
"cache_read": 0.12,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 512000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 0.6,
|
|
"output": 2.4,
|
|
"cache_read": 0.12
|
|
}
|
|
}
|
|
},
|
|
"MiniMax-M3.1-Flash": {
|
|
"id": "MiniMax-M3.1-Flash",
|
|
"canonical_model_id": "minimax/MiniMax-M3.1-Flash",
|
|
"name": "MiniMax-M3.1-Flash",
|
|
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
|
|
"family": "minimax",
|
|
"release_date": "2026-10-19",
|
|
"last_updated": "2026-10-19",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": false,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 524288
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.6,
|
|
"cache_read": 0.015
|
|
}
|
|
}
|
|
},
|
|
"moonshotai": {
|
|
"kimi-k2.6": {
|
|
"id": "kimi-k2.6",
|
|
"canonical_model_id": "moonshotai/kimi-k2.6",
|
|
"name": "Kimi K2.6",
|
|
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
|
|
"family": "kimi-k2",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-04-20",
|
|
"last_updated": "2026-04-20",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 262144
|
|
},
|
|
"cost": {
|
|
"input": 0.95,
|
|
"output": 4,
|
|
"cache_read": 0.16
|
|
}
|
|
},
|
|
"kimi-k2.7-code": {
|
|
"id": "kimi-k2.7-code",
|
|
"canonical_model_id": "moonshotai/kimi-k2.7-code",
|
|
"name": "Kimi K2.7 Code",
|
|
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
|
|
"family": "kimi-k2",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-06-12",
|
|
"last_updated": "2026-06-12",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 262144
|
|
},
|
|
"cost": {
|
|
"input": 0.95,
|
|
"output": 4,
|
|
"cache_read": 0.19
|
|
}
|
|
},
|
|
"kimi-k2.7-code-highspeed": {
|
|
"id": "kimi-k2.7-code-highspeed",
|
|
"canonical_model_id": "moonshotai/kimi-k2.7-code",
|
|
"name": "Kimi K2.7 Code HighSpeed",
|
|
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
|
|
"family": "kimi-k2",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-06-12",
|
|
"last_updated": "2026-06-12",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 262144
|
|
},
|
|
"cost": {
|
|
"input": 1.9,
|
|
"output": 8,
|
|
"cache_read": 0.38
|
|
}
|
|
},
|
|
"kimi-k3": {
|
|
"id": "kimi-k3",
|
|
"canonical_model_id": "moonshotai/kimi-k3",
|
|
"name": "Kimi K3",
|
|
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
|
|
"family": "kimi-k3",
|
|
"release_date": "2026-07-16",
|
|
"last_updated": "2026-07-16",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 1048576
|
|
},
|
|
"cost": {
|
|
"input": 3,
|
|
"output": 15,
|
|
"cache_read": 0.3,
|
|
"cache_write": 3
|
|
}
|
|
},
|
|
"kimi-k3.1-pro": {
|
|
"id": "kimi-k3.1-pro",
|
|
"canonical_model_id": "moonshotai/kimi-k3.1-pro",
|
|
"name": "Kimi K3.1 Pro",
|
|
"description": "Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work",
|
|
"family": "kimi-k3",
|
|
"release_date": "2026-10-23",
|
|
"last_updated": "2026-10-23",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 1048576
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.2,
|
|
"cache_write": 2
|
|
}
|
|
},
|
|
"kimi-k3.1-pro-highspeed": {
|
|
"id": "kimi-k3.1-pro-highspeed",
|
|
"canonical_model_id": "moonshotai/kimi-k3.1-pro",
|
|
"name": "Kimi K3.1 Pro Highspeed",
|
|
"description": "Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work",
|
|
"family": "kimi-k3",
|
|
"release_date": "2026-10-23",
|
|
"last_updated": "2026-10-23",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 1048576
|
|
},
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.2,
|
|
"cache_write": 4
|
|
}
|
|
}
|
|
},
|
|
"novita-ai": {
|
|
"deepseek/deepseek-v4-pro": {
|
|
"id": "deepseek/deepseek-v4-pro",
|
|
"canonical_model_id": "deepseek/deepseek-v4-pro",
|
|
"name": "DeepSeek V4 Pro",
|
|
"description": "Open MoE flagship with million-token context for coding and long agent runs",
|
|
"family": "deepseek-thinking",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-04-24",
|
|
"last_updated": "2026-04-24",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 393216
|
|
},
|
|
"cost": {
|
|
"input": 1.6,
|
|
"output": 3.2,
|
|
"cache_read": 0.135
|
|
}
|
|
}
|
|
},
|
|
"openai": {
|
|
"gpt-5.3-codex": {
|
|
"id": "gpt-5.3-codex",
|
|
"name": "GPT-5.3 Codex",
|
|
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
|
|
"family": "gpt-codex",
|
|
"knowledge": "2025-08-31",
|
|
"release_date": "2026-02-05",
|
|
"last_updated": "2026-02-05",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 400000,
|
|
"input": 272000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 1.75,
|
|
"output": 14,
|
|
"cache_read": 0.175
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 3.5,
|
|
"output": 28,
|
|
"cache_read": 0.35
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-5.5": {
|
|
"id": "gpt-5.5",
|
|
"name": "GPT-5.5",
|
|
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
|
|
"family": "gpt",
|
|
"knowledge": "2025-12-01",
|
|
"release_date": "2026-04-23",
|
|
"last_updated": "2026-04-23",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 5,
|
|
"output": 30,
|
|
"cache_read": 0.5,
|
|
"tiers": [
|
|
{
|
|
"input": 10,
|
|
"output": 45,
|
|
"cache_read": 1,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 10,
|
|
"output": 45,
|
|
"cache_read": 1
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 12.5,
|
|
"output": 75,
|
|
"cache_read": 1.25
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-5.5-pro": {
|
|
"id": "gpt-5.5-pro",
|
|
"name": "GPT-5.5 Pro",
|
|
"description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding",
|
|
"family": "gpt-pro",
|
|
"knowledge": "2025-12-01",
|
|
"release_date": "2026-04-23",
|
|
"last_updated": "2026-04-23",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 30,
|
|
"output": 180,
|
|
"tiers": [
|
|
{
|
|
"input": 60,
|
|
"output": 270,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 60,
|
|
"output": 270
|
|
}
|
|
}
|
|
},
|
|
"gpt-5.6": {
|
|
"id": "gpt-5.6",
|
|
"canonical_model_id": "openai/gpt-5.6-sol",
|
|
"name": "GPT-5.6",
|
|
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
|
|
"family": "gpt-sol",
|
|
"knowledge": "2026-02-16",
|
|
"release_date": "2026-07-09",
|
|
"last_updated": "2026-07-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5,
|
|
"tiers": [
|
|
{
|
|
"input": 8,
|
|
"output": 30,
|
|
"cache_read": 0.8,
|
|
"cache_write": 10,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 8,
|
|
"output": 30,
|
|
"cache_read": 0.8,
|
|
"cache_write": 10
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 8,
|
|
"output": 40,
|
|
"cache_read": 0.8,
|
|
"cache_write": 10
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-5.6-luna": {
|
|
"id": "gpt-5.6-luna",
|
|
"canonical_model_id": "openai/gpt-5.6-luna",
|
|
"name": "GPT-5.6 Luna",
|
|
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
|
|
"family": "gpt-luna",
|
|
"knowledge": "2026-02-16",
|
|
"release_date": "2026-07-09",
|
|
"last_updated": "2026-07-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 0.2,
|
|
"output": 1.2,
|
|
"cache_read": 0.02,
|
|
"cache_write": 0.25,
|
|
"tiers": [
|
|
{
|
|
"input": 0.4,
|
|
"output": 1.8,
|
|
"cache_read": 0.04,
|
|
"cache_write": 0.5,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 0.4,
|
|
"output": 1.8,
|
|
"cache_read": 0.04,
|
|
"cache_write": 0.5
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 0.4,
|
|
"output": 2.4,
|
|
"cache_read": 0.04,
|
|
"cache_write": 0.5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-5.6-sol": {
|
|
"id": "gpt-5.6-sol",
|
|
"canonical_model_id": "openai/gpt-5.6-sol",
|
|
"name": "GPT-5.6 Sol",
|
|
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
|
|
"family": "gpt-sol",
|
|
"knowledge": "2026-02-16",
|
|
"release_date": "2026-07-09",
|
|
"last_updated": "2026-07-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5,
|
|
"tiers": [
|
|
{
|
|
"input": 8,
|
|
"output": 30,
|
|
"cache_read": 0.8,
|
|
"cache_write": 10,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 8,
|
|
"output": 30,
|
|
"cache_read": 0.8,
|
|
"cache_write": 10
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 8,
|
|
"output": 40,
|
|
"cache_read": 0.8,
|
|
"cache_write": 10
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-5.6-terra": {
|
|
"id": "gpt-5.6-terra",
|
|
"canonical_model_id": "openai/gpt-5.6-terra",
|
|
"name": "GPT-5.6 Terra",
|
|
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
|
|
"family": "gpt-terra",
|
|
"knowledge": "2026-02-16",
|
|
"release_date": "2026-07-09",
|
|
"last_updated": "2026-07-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 12,
|
|
"cache_read": 0.2,
|
|
"cache_write": 2.5,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 18,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 18,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 24,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-6-astra": {
|
|
"id": "gpt-6-astra",
|
|
"canonical_model_id": "openai/gpt-6-astra",
|
|
"name": "GPT-6 Astra",
|
|
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
|
|
"family": "gpt-astra",
|
|
"knowledge": "2026-04-30",
|
|
"release_date": "2026-09-04",
|
|
"last_updated": "2026-09-04",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 10,
|
|
"output": 50,
|
|
"cache_read": 1,
|
|
"cache_write": 12.5,
|
|
"tiers": [
|
|
{
|
|
"input": 20,
|
|
"output": 75,
|
|
"cache_read": 2,
|
|
"cache_write": 25,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 20,
|
|
"output": 75,
|
|
"cache_read": 2,
|
|
"cache_write": 25
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 20,
|
|
"output": 100,
|
|
"cache_read": 2,
|
|
"cache_write": 25
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"ultrafast": {
|
|
"cost": {
|
|
"input": 60,
|
|
"output": 300,
|
|
"cache_read": 6,
|
|
"cache_write": 75
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "ultrafast"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-6-luna": {
|
|
"id": "gpt-6-luna",
|
|
"canonical_model_id": "openai/gpt-6-luna",
|
|
"name": "GPT-6 Luna",
|
|
"description": "OpenAI's most efficient model for focused, high-volume tasks",
|
|
"family": "gpt-luna",
|
|
"knowledge": "2026-05-18",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 0.1,
|
|
"output": 0.5,
|
|
"cache_read": 0.01,
|
|
"cache_write": 0.125,
|
|
"tiers": [
|
|
{
|
|
"input": 0.2,
|
|
"output": 0.75,
|
|
"cache_read": 0.02,
|
|
"cache_write": 0.25,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 0.2,
|
|
"output": 0.75,
|
|
"cache_read": 0.02,
|
|
"cache_write": 0.25
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 0.2,
|
|
"output": 1,
|
|
"cache_read": 0.02,
|
|
"cache_write": 0.25
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-6-sol": {
|
|
"id": "gpt-6-sol",
|
|
"canonical_model_id": "openai/gpt-6-sol",
|
|
"name": "GPT-6 Sol",
|
|
"description": "OpenAI model for complex coding and agentic workflows",
|
|
"family": "gpt-sol",
|
|
"knowledge": "2026-04-20",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.2,
|
|
"cache_write": 2.5,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 15,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 15,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-6.1-sol": {
|
|
"id": "gpt-6.1-sol",
|
|
"canonical_model_id": "openai/gpt-6.1-sol",
|
|
"name": "GPT-6.1 Sol",
|
|
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
|
|
"family": "gpt-sol",
|
|
"knowledge": "2026-04-30",
|
|
"release_date": "2026-09-29",
|
|
"last_updated": "2026-09-29",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.1,
|
|
"cache_write": 2.5,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 15,
|
|
"cache_read": 0.2,
|
|
"cache_write": 5,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 15,
|
|
"cache_read": 0.2,
|
|
"cache_write": 5
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.2,
|
|
"cache_write": 5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"ultrafast": {
|
|
"cost": {
|
|
"input": 12,
|
|
"output": 60,
|
|
"cache_read": 0.6,
|
|
"cache_write": 15
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "ultrafast"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"gpt-6.1-terra": {
|
|
"id": "gpt-6.1-terra",
|
|
"canonical_model_id": "openai/gpt-6.1-terra",
|
|
"name": "GPT-6.1 Terra",
|
|
"description": "Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.",
|
|
"family": "gpt-terra",
|
|
"knowledge": "2026-06-01",
|
|
"release_date": "2026-10-26",
|
|
"last_updated": "2026-10-26",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 1,
|
|
"output": 5,
|
|
"cache_read": 0.05,
|
|
"cache_write": 1.25,
|
|
"tiers": [
|
|
{
|
|
"input": 2,
|
|
"output": 7.5,
|
|
"cache_read": 0.1,
|
|
"cache_write": 2.5,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 2,
|
|
"output": 7.5,
|
|
"cache_read": 0.1,
|
|
"cache_write": 2.5
|
|
}
|
|
},
|
|
"experimental": {
|
|
"modes": {
|
|
"fast": {
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.1,
|
|
"cache_write": 2.5
|
|
},
|
|
"provider": {
|
|
"body": {
|
|
"service_tier": "priority"
|
|
}
|
|
}
|
|
},
|
|
"pro": {
|
|
"provider": {
|
|
"body": {
|
|
"reasoning": {
|
|
"mode": "pro"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"openrouter": {
|
|
"deepseek/deepseek-v4-flash": {
|
|
"id": "deepseek/deepseek-v4-flash",
|
|
"canonical_model_id": "deepseek/deepseek-v4-flash",
|
|
"name": "DeepSeek V4 Flash",
|
|
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-04-24",
|
|
"last_updated": "2026-04-24",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 943717
|
|
},
|
|
"cost": {
|
|
"input": 0.091,
|
|
"output": 0.182,
|
|
"cache_read": 0.0182
|
|
}
|
|
},
|
|
"deepseek/deepseek-v4-pro": {
|
|
"id": "deepseek/deepseek-v4-pro",
|
|
"canonical_model_id": "deepseek/deepseek-v4-pro",
|
|
"name": "DeepSeek V4 Pro",
|
|
"description": "Open MoE flagship with million-token context for coding and long agent runs",
|
|
"family": "deepseek-thinking",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-04-24",
|
|
"last_updated": "2026-04-24",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 0.95526,
|
|
"output": 1.91052,
|
|
"cache_read": 0.079605
|
|
}
|
|
},
|
|
"dots-studio/dots-3-note-preview:free": {
|
|
"id": "dots-studio/dots-3-note-preview:free",
|
|
"name": "Dots3-Note Preview (free)",
|
|
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
|
|
"release_date": "2026-08-14",
|
|
"last_updated": "2026-08-14",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 512000,
|
|
"output": 460800
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0
|
|
},
|
|
"status": "deprecated"
|
|
},
|
|
"minimax/minimax-m3": {
|
|
"id": "minimax/minimax-m3",
|
|
"canonical_model_id": "minimax/MiniMax-M3",
|
|
"name": "MiniMax-M3",
|
|
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
|
|
"family": "minimax",
|
|
"release_date": "2026-06-01",
|
|
"last_updated": "2026-06-01",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 512000
|
|
},
|
|
"cost": {
|
|
"input": 0.3,
|
|
"output": 1.2,
|
|
"cache_read": 0.06
|
|
}
|
|
},
|
|
"qwen/qwen3.6-35b-a3b": {
|
|
"id": "qwen/qwen3.6-35b-a3b",
|
|
"canonical_model_id": "alibaba/qwen3.6-35b-a3b",
|
|
"name": "Qwen3.6 35B-A3B",
|
|
"description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
|
|
"family": "qwen",
|
|
"release_date": "2026-04-17",
|
|
"last_updated": "2026-04-17",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 235929
|
|
},
|
|
"cost": {
|
|
"input": 0.1,
|
|
"output": 0.9,
|
|
"cache_read": 0.025
|
|
}
|
|
},
|
|
"qwen/qwen3.6-flash": {
|
|
"id": "qwen/qwen3.6-flash",
|
|
"canonical_model_id": "alibaba/qwen3.6-flash",
|
|
"name": "Qwen3.6 Flash",
|
|
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
|
|
"family": "qwen3.6",
|
|
"release_date": "2026-04-27",
|
|
"last_updated": "2026-04-27",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.1875,
|
|
"output": 1.125,
|
|
"cache_write": 0.234375,
|
|
"tiers": [
|
|
{
|
|
"input": 0.75,
|
|
"output": 3,
|
|
"cache_write": 0.9375,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 256000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 0.75,
|
|
"output": 3,
|
|
"cache_write": 0.9375
|
|
}
|
|
}
|
|
},
|
|
"qwen/qwen3.6-plus": {
|
|
"id": "qwen/qwen3.6-plus",
|
|
"canonical_model_id": "alibaba/qwen3.6-plus",
|
|
"name": "Qwen3.6 Plus",
|
|
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
|
|
"family": "qwen",
|
|
"knowledge": "2025-04",
|
|
"release_date": "2026-04-02",
|
|
"last_updated": "2026-04-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.325,
|
|
"output": 1.95,
|
|
"cache_write": 0.40625,
|
|
"tiers": [
|
|
{
|
|
"input": 1.3,
|
|
"output": 3.9,
|
|
"cache_write": 1.625,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 256000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 1.3,
|
|
"output": 3.9,
|
|
"cache_write": 1.625
|
|
}
|
|
}
|
|
},
|
|
"qwen/qwen3.7-plus": {
|
|
"id": "qwen/qwen3.7-plus",
|
|
"canonical_model_id": "alibaba/qwen3.7-plus",
|
|
"name": "Qwen3.7 Plus",
|
|
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
|
|
"family": "qwen",
|
|
"knowledge": "2025-04",
|
|
"release_date": "2026-06-02",
|
|
"last_updated": "2026-06-02",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.32,
|
|
"output": 1.28,
|
|
"cache_read": 0.064,
|
|
"cache_write": 0.4,
|
|
"tiers": [
|
|
{
|
|
"input": 0.96,
|
|
"output": 3.84,
|
|
"cache_read": 0.192,
|
|
"cache_write": 1.2,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 256000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 0.96,
|
|
"output": 3.84,
|
|
"cache_read": 0.192,
|
|
"cache_write": 1.2
|
|
}
|
|
}
|
|
},
|
|
"qwen/qwen3.8-flash": {
|
|
"id": "qwen/qwen3.8-flash",
|
|
"canonical_model_id": "alibaba/qwen3.8-flash",
|
|
"name": "Qwen3.8 Flash",
|
|
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
|
|
"family": "qwen",
|
|
"release_date": "2026-08-26",
|
|
"last_updated": "2026-08-26",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "budget_tokens"
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.47,
|
|
"cache_read": 0.016
|
|
}
|
|
},
|
|
"tencent/hy4": {
|
|
"id": "tencent/hy4",
|
|
"canonical_model_id": "tencent/hy4",
|
|
"name": "Hy4",
|
|
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
|
|
"family": "Hy",
|
|
"release_date": "2026-11-04",
|
|
"last_updated": "2026-11-04",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"input": 983010,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.417,
|
|
"output": 1.2505,
|
|
"cache_read": 0.021
|
|
}
|
|
},
|
|
"z-ai/glm-5.2": {
|
|
"id": "z-ai/glm-5.2",
|
|
"canonical_model_id": "zhipuai/glm-5.2",
|
|
"name": "GLM-5.2",
|
|
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
|
|
"family": "glm",
|
|
"release_date": "2026-06-13",
|
|
"last_updated": "2026-06-13",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 943718
|
|
},
|
|
"cost": {
|
|
"input": 0.006,
|
|
"output": 6.8,
|
|
"cache_read": 0.005
|
|
}
|
|
},
|
|
"z-ai/glm-5.3": {
|
|
"id": "z-ai/glm-5.3",
|
|
"canonical_model_id": "zhipuai/glm-5.3",
|
|
"name": "GLM-5.3",
|
|
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
|
|
"family": "glm",
|
|
"release_date": "2026-08-14",
|
|
"last_updated": "2026-08-14",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 943718
|
|
},
|
|
"cost": {
|
|
"input": 0.0699,
|
|
"output": 1.4,
|
|
"cache_read": 0.0689
|
|
}
|
|
},
|
|
"z-ai/glm-5.3-flash": {
|
|
"id": "z-ai/glm-5.3-flash",
|
|
"canonical_model_id": "zhipuai/glm-5.3-flash",
|
|
"name": "GLM-5.3-Flash",
|
|
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
|
|
"family": "glm-flash",
|
|
"release_date": "2026-08-26",
|
|
"last_updated": "2026-08-26",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 943717
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.5,
|
|
"cache_read": 0.03
|
|
}
|
|
}
|
|
},
|
|
"orcarouter": {
|
|
"anthropic/claude-opus-5": {
|
|
"id": "anthropic/claude-opus-5",
|
|
"canonical_model_id": "anthropic/claude-opus-5",
|
|
"name": "Claude Opus 5",
|
|
"description": "Strongest Claude Opus model for coding, agents, and professional work",
|
|
"family": "claude-opus",
|
|
"knowledge": "2026-05",
|
|
"release_date": "2026-07-24",
|
|
"last_updated": "2026-07-24",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 5,
|
|
"output": 25,
|
|
"cache_read": 0.5,
|
|
"cache_write": 10
|
|
}
|
|
},
|
|
"anthropic/claude-sonnet-5": {
|
|
"id": "anthropic/claude-sonnet-5",
|
|
"canonical_model_id": "anthropic/claude-sonnet-5",
|
|
"name": "Claude Sonnet 5",
|
|
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
|
|
"family": "claude-sonnet",
|
|
"knowledge": "2026-01-31",
|
|
"release_date": "2026-06-30",
|
|
"last_updated": "2026-06-30",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 10,
|
|
"cache_read": 0.2,
|
|
"cache_write": 2.5
|
|
}
|
|
},
|
|
"deepseek/deepseek-v4-flash-0731": {
|
|
"id": "deepseek/deepseek-v4-flash-0731",
|
|
"canonical_model_id": "deepseek/deepseek-v4-flash-0731",
|
|
"name": "DeepSeek V4 Flash 0731",
|
|
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-07-31",
|
|
"last_updated": "2026-07-31",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 0.22,
|
|
"output": 0.66,
|
|
"cache_read": 0.007
|
|
}
|
|
},
|
|
"deepseek/deepseek-v4-pro-0813": {
|
|
"id": "deepseek/deepseek-v4-pro-0813",
|
|
"canonical_model_id": "deepseek/deepseek-v4-pro-0813",
|
|
"name": "DeepSeek V4 Pro 0813",
|
|
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
|
|
"family": "deepseek-thinking",
|
|
"release_date": "2026-08-13",
|
|
"last_updated": "2026-08-22",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 0.66,
|
|
"output": 1.98,
|
|
"cache_read": 0.022
|
|
}
|
|
},
|
|
"google/gemini-flash-latest": {
|
|
"id": "google/gemini-flash-latest",
|
|
"canonical_model_id": "google/gemini-flash-latest",
|
|
"name": "Gemini Flash Latest",
|
|
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
|
|
"family": "gemini-flash",
|
|
"knowledge": "2026-03",
|
|
"release_date": "2026-08-13",
|
|
"last_updated": "2026-08-13",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"audio",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 0.5,
|
|
"output": 3,
|
|
"cache_read": 0.1
|
|
}
|
|
},
|
|
"grok/grok-4.6": {
|
|
"id": "grok/grok-4.6",
|
|
"canonical_model_id": "xai/grok-4.6",
|
|
"name": "Grok 4.6",
|
|
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
|
|
"family": "grok",
|
|
"knowledge": "2026-02-01",
|
|
"release_date": "2026-08-12",
|
|
"last_updated": "2026-08-12",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 500000,
|
|
"output": 500000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 6,
|
|
"cache_read": 0.5,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 1,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 200000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 1
|
|
}
|
|
}
|
|
},
|
|
"kimi/kimi-k3": {
|
|
"id": "kimi/kimi-k3",
|
|
"canonical_model_id": "moonshotai/kimi-k3",
|
|
"name": "Kimi K3",
|
|
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
|
|
"family": "kimi-k3",
|
|
"release_date": "2026-07-16",
|
|
"last_updated": "2026-07-16",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 3,
|
|
"output": 15,
|
|
"cache_read": 0.3
|
|
}
|
|
},
|
|
"meta/muse-spark-1.2": {
|
|
"id": "meta/muse-spark-1.2",
|
|
"canonical_model_id": "meta/muse-spark-1.2",
|
|
"name": "Muse Spark 1.2",
|
|
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
|
|
"family": "muse",
|
|
"release_date": "2026-08-05",
|
|
"last_updated": "2026-08-05",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"minimal",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf",
|
|
"audio"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.25,
|
|
"output": 4.25,
|
|
"cache_read": 0.15
|
|
}
|
|
},
|
|
"openai/gpt-5.6-sol": {
|
|
"id": "openai/gpt-5.6-sol",
|
|
"canonical_model_id": "openai/gpt-5.6-sol",
|
|
"name": "GPT-5.6 Sol",
|
|
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
|
|
"family": "gpt-sol",
|
|
"knowledge": "2026-02-16",
|
|
"release_date": "2026-07-09",
|
|
"last_updated": "2026-07-09",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": false,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1050000,
|
|
"input": 922000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 4,
|
|
"output": 20,
|
|
"cache_read": 0.4,
|
|
"cache_write": 5,
|
|
"tiers": [
|
|
{
|
|
"input": 8,
|
|
"output": 30,
|
|
"cache_read": 0.8,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 272000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 8,
|
|
"output": 30,
|
|
"cache_read": 0.8
|
|
}
|
|
}
|
|
},
|
|
"orcarouter/free": {
|
|
"id": "orcarouter/free",
|
|
"name": "OrcaRouter Free",
|
|
"description": "Built-in router over the free tier that scores each request's difficulty and sends light work to the smaller free model and harder work to the stronger one. Priced at zero and never falls back to a paid model.",
|
|
"family": "auto",
|
|
"release_date": "2026-08-27",
|
|
"last_updated": "2026-08-27",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 65536,
|
|
"output": 32768
|
|
},
|
|
"cost": {
|
|
"input": 0,
|
|
"output": 0
|
|
}
|
|
},
|
|
"qwen/qwen3.8-27b": {
|
|
"id": "qwen/qwen3.8-27b",
|
|
"canonical_model_id": "alibaba/qwen3.8-27b",
|
|
"name": "Qwen3.8 27B",
|
|
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
|
|
"family": "qwen",
|
|
"release_date": "2026-08-14",
|
|
"last_updated": "2026-08-14",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 262144,
|
|
"output": 32768
|
|
},
|
|
"cost": {
|
|
"input": 0.33,
|
|
"output": 2.4
|
|
}
|
|
},
|
|
"qwen/qwen3.8-max": {
|
|
"id": "qwen/qwen3.8-max",
|
|
"canonical_model_id": "alibaba/qwen3.8-max",
|
|
"name": "Qwen3.8 Max",
|
|
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
|
|
"family": "qwen",
|
|
"release_date": "2026-08-03",
|
|
"last_updated": "2026-08-03",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"xhigh"
|
|
]
|
|
},
|
|
{
|
|
"type": "budget_tokens",
|
|
"min": 0,
|
|
"max": 262144
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 6,
|
|
"cache_read": 0.25,
|
|
"cache_write": 2.5
|
|
}
|
|
},
|
|
"tencent/hy3": {
|
|
"id": "tencent/hy3",
|
|
"canonical_model_id": "tencent/hy3",
|
|
"name": "Hy3",
|
|
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
|
|
"family": "Hy",
|
|
"release_date": "2026-07-06",
|
|
"last_updated": "2026-07-06",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 256000,
|
|
"input": 192000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 0.18,
|
|
"output": 0.59,
|
|
"cache_read": 0.059
|
|
}
|
|
},
|
|
"z-ai/glm-5.3": {
|
|
"id": "z-ai/glm-5.3",
|
|
"canonical_model_id": "zhipuai/glm-5.3",
|
|
"name": "GLM-5.3",
|
|
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
|
|
"family": "glm",
|
|
"release_date": "2026-08-14",
|
|
"last_updated": "2026-08-14",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.26,
|
|
"output": 3.96,
|
|
"cache_read": 0.234
|
|
}
|
|
},
|
|
"z-ai/glm-5.3-flash": {
|
|
"id": "z-ai/glm-5.3-flash",
|
|
"canonical_model_id": "zhipuai/glm-5.3-flash",
|
|
"name": "GLM-5.3-Flash",
|
|
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
|
|
"family": "glm-flash",
|
|
"release_date": "2026-08-26",
|
|
"last_updated": "2026-08-26",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 128000
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.5,
|
|
"cache_read": 0.03
|
|
}
|
|
}
|
|
},
|
|
"siliconflow": {
|
|
"deepseek-ai/DeepSeek-V4-Flash": {
|
|
"id": "deepseek-ai/DeepSeek-V4-Flash",
|
|
"canonical_model_id": "deepseek/deepseek-v4-flash",
|
|
"name": "DeepSeek V4 Flash",
|
|
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
|
|
"family": "deepseek-flash",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-04-24",
|
|
"last_updated": "2026-04-24",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "budget_tokens",
|
|
"min": 128,
|
|
"max": 32768
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 0.13,
|
|
"output": 0.28,
|
|
"cache_read": 0.028
|
|
}
|
|
},
|
|
"deepseek-ai/DeepSeek-V4-Pro": {
|
|
"id": "deepseek-ai/DeepSeek-V4-Pro",
|
|
"canonical_model_id": "deepseek/deepseek-v4-pro",
|
|
"name": "DeepSeek V4 Pro",
|
|
"description": "Open MoE flagship with million-token context for coding and long agent runs",
|
|
"family": "deepseek-thinking",
|
|
"knowledge": "2025-05",
|
|
"release_date": "2026-04-24",
|
|
"last_updated": "2026-04-24",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "budget_tokens",
|
|
"min": 128,
|
|
"max": 32768
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 384000
|
|
},
|
|
"cost": {
|
|
"input": 1.50162,
|
|
"output": 3.135,
|
|
"cache_read": 0.135
|
|
}
|
|
}
|
|
},
|
|
"stepfun": {
|
|
"step-3.5-flash": {
|
|
"id": "step-3.5-flash",
|
|
"canonical_model_id": "stepfun/step-3.5-flash",
|
|
"name": "Step 3.5 Flash",
|
|
"description": "StepFun flash lane for quick multimodal reasoning and coding assistance",
|
|
"family": "step",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-01-29",
|
|
"last_updated": "2026-02-13",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 256000,
|
|
"input": 256000,
|
|
"output": 256000
|
|
},
|
|
"cost": {
|
|
"input": 0.10461,
|
|
"output": 0.31384,
|
|
"cache_read": 0.02092
|
|
}
|
|
},
|
|
"step-3.5-flash-2603": {
|
|
"id": "step-3.5-flash-2603",
|
|
"canonical_model_id": "stepfun/step-3.5-flash-2603",
|
|
"name": "Step 3.5 Flash 2603",
|
|
"description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
|
|
"family": "step",
|
|
"knowledge": "2025-01",
|
|
"release_date": "2026-04-02",
|
|
"last_updated": "2026-04-02",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 256000,
|
|
"input": 256000,
|
|
"output": 256000
|
|
},
|
|
"cost": {
|
|
"input": 0.10461,
|
|
"output": 0.31384,
|
|
"cache_read": 0.02092
|
|
}
|
|
},
|
|
"step-3.7-flash": {
|
|
"id": "step-3.7-flash",
|
|
"canonical_model_id": "stepfun/step-3.7-flash",
|
|
"name": "Step 3.7 Flash",
|
|
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
|
|
"knowledge": "2026-03-01",
|
|
"release_date": "2026-05-29",
|
|
"last_updated": "2026-05-29",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 256000,
|
|
"input": 256000,
|
|
"output": 256000
|
|
},
|
|
"cost": {
|
|
"input": 0.20175,
|
|
"output": 1.21052,
|
|
"cache_read": 0.04035
|
|
}
|
|
},
|
|
"step-5-preview": {
|
|
"id": "step-5-preview",
|
|
"canonical_model_id": "stepfun/step-5-preview",
|
|
"name": "Step 5 Preview",
|
|
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
|
|
"release_date": "2026-09-16",
|
|
"last_updated": "2026-09-20",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"input": 1000000,
|
|
"output": 65536
|
|
},
|
|
"cost": {
|
|
"input": 1.04613,
|
|
"output": 2.98895,
|
|
"cache_read": 0.10461
|
|
}
|
|
}
|
|
},
|
|
"xai": {
|
|
"grok-4.3": {
|
|
"id": "grok-4.3",
|
|
"name": "Grok 4.3",
|
|
"description": "xAI's Grok for chat, coding, agentic tools, and lower hallucination risk",
|
|
"family": "grok",
|
|
"release_date": "2026-04-17",
|
|
"last_updated": "2026-04-17",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"none",
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 30000
|
|
},
|
|
"cost": {
|
|
"input": 1.25,
|
|
"output": 2.5,
|
|
"cache_read": 0.2,
|
|
"tiers": [
|
|
{
|
|
"input": 2.5,
|
|
"output": 5,
|
|
"cache_read": 0.4,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 200000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 2.5,
|
|
"output": 5,
|
|
"cache_read": 0.4
|
|
}
|
|
}
|
|
},
|
|
"grok-4.5": {
|
|
"id": "grok-4.5",
|
|
"canonical_model_id": "xai/grok-4.5",
|
|
"name": "Grok 4.5",
|
|
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
|
|
"family": "grok",
|
|
"release_date": "2026-07-08",
|
|
"last_updated": "2026-07-08",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 500000,
|
|
"output": 500000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 6,
|
|
"cache_read": 0.3,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 0.6,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 200000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 0.6
|
|
}
|
|
}
|
|
},
|
|
"grok-4.6": {
|
|
"id": "grok-4.6",
|
|
"canonical_model_id": "xai/grok-4.6",
|
|
"name": "Grok 4.6",
|
|
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
|
|
"family": "grok",
|
|
"knowledge": "2026-02-01",
|
|
"release_date": "2026-08-12",
|
|
"last_updated": "2026-08-12",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 500000,
|
|
"output": 500000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 6,
|
|
"cache_read": 0.5,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 1,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 200000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 1
|
|
}
|
|
}
|
|
},
|
|
"grok-4.7": {
|
|
"id": "grok-4.7",
|
|
"canonical_model_id": "xai/grok-4.7",
|
|
"name": "Grok 4.7",
|
|
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
|
|
"family": "grok",
|
|
"knowledge": "2026-05",
|
|
"release_date": "2026-09-21",
|
|
"last_updated": "2026-09-21",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"medium",
|
|
"high",
|
|
"xhigh"
|
|
]
|
|
}
|
|
],
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 500000,
|
|
"output": 500000
|
|
},
|
|
"cost": {
|
|
"input": 2,
|
|
"output": 6,
|
|
"cache_read": 0.5,
|
|
"tiers": [
|
|
{
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 1,
|
|
"tier": {
|
|
"type": "context",
|
|
"size": 200000
|
|
}
|
|
}
|
|
],
|
|
"context_over_200k": {
|
|
"input": 4,
|
|
"output": 12,
|
|
"cache_read": 1
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"xiaomi": {
|
|
"mimo-v2.6-flash": {
|
|
"id": "mimo-v2.6-flash",
|
|
"canonical_model_id": "xiaomi/mimo-v2.6-flash",
|
|
"name": "MiMo-V2.6-Flash",
|
|
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
|
|
"family": "mimo",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"audio",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.14,
|
|
"output": 0.28,
|
|
"cache_read": 0.0028
|
|
}
|
|
},
|
|
"mimo-v2.6-pro": {
|
|
"id": "mimo-v2.6-pro",
|
|
"canonical_model_id": "xiaomi/mimo-v2.6-pro",
|
|
"name": "MiMo-V2.6-Pro",
|
|
"description": "MiMo Pro model for multimodal coding agents and long-context automation",
|
|
"family": "mimo",
|
|
"release_date": "2026-09-22",
|
|
"last_updated": "2026-09-22",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"audio",
|
|
"video"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1048576,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.435,
|
|
"output": 0.87,
|
|
"cache_read": 0.0036
|
|
}
|
|
}
|
|
},
|
|
"zai": {
|
|
"glm-5-turbo": {
|
|
"id": "glm-5-turbo",
|
|
"canonical_model_id": "zhipuai/glm-5-turbo",
|
|
"name": "GLM-5-Turbo",
|
|
"description": "Faster GLM-5 lane for coding agents that need lower latency",
|
|
"family": "glm",
|
|
"release_date": "2026-03-16",
|
|
"last_updated": "2026-03-16",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": false,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 200000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.2,
|
|
"output": 4,
|
|
"cache_read": 0.24,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"glm-5.1": {
|
|
"id": "glm-5.1",
|
|
"canonical_model_id": "zhipuai/glm-5.1",
|
|
"name": "GLM-5.1",
|
|
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
|
|
"family": "glm",
|
|
"release_date": "2026-04-07",
|
|
"last_updated": "2026-04-07",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 200000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.4,
|
|
"output": 4.4,
|
|
"cache_read": 0.26,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"glm-5.2": {
|
|
"id": "glm-5.2",
|
|
"canonical_model_id": "zhipuai/glm-5.2",
|
|
"name": "GLM-5.2",
|
|
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
|
|
"family": "glm",
|
|
"release_date": "2026-06-13",
|
|
"last_updated": "2026-06-13",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "toggle"
|
|
},
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.4,
|
|
"output": 4.4,
|
|
"cache_read": 0.26,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"glm-5.3": {
|
|
"id": "glm-5.3",
|
|
"canonical_model_id": "zhipuai/glm-5.3",
|
|
"name": "GLM-5.3",
|
|
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
|
|
"family": "glm",
|
|
"release_date": "2026-08-14",
|
|
"last_updated": "2026-08-14",
|
|
"attachment": false,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 1.4,
|
|
"output": 4.4,
|
|
"cache_read": 0.26,
|
|
"cache_write": 0
|
|
}
|
|
},
|
|
"glm-5.3-flash": {
|
|
"id": "glm-5.3-flash",
|
|
"canonical_model_id": "zhipuai/glm-5.3-flash",
|
|
"name": "GLM-5.3-Flash",
|
|
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
|
|
"family": "glm-flash",
|
|
"release_date": "2026-08-26",
|
|
"last_updated": "2026-08-26",
|
|
"attachment": true,
|
|
"reasoning": true,
|
|
"reasoning_options": [
|
|
{
|
|
"type": "effort",
|
|
"values": [
|
|
"low",
|
|
"high",
|
|
"max"
|
|
]
|
|
}
|
|
],
|
|
"interleaved": {
|
|
"field": "reasoning_content"
|
|
},
|
|
"tool_call": true,
|
|
"structured_output": true,
|
|
"temperature": true,
|
|
"open_weights": true,
|
|
"modalities": {
|
|
"input": [
|
|
"text",
|
|
"image",
|
|
"video",
|
|
"pdf"
|
|
],
|
|
"output": [
|
|
"text"
|
|
]
|
|
},
|
|
"limit": {
|
|
"context": 1000000,
|
|
"output": 131072
|
|
},
|
|
"cost": {
|
|
"input": 0.15,
|
|
"output": 0.5,
|
|
"cache_read": 0.03,
|
|
"cache_write": 0
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|