codewhale-hq/Codewhale
1
0 Fork 0
mirror of https://github.com/codewhale-hq/Codewhale.git synced 2026-11-07 17:09:13 -10:00
Code Issues Packages Projects Releases 1 Wiki Activity

chore(catalog): re-lock the offline seed to the 2026-10-23 Models.dev refresh (#6396 item 13)

Browse Source 
The seed lock had not been refreshed since 2026-10-17 and upstream retargeted
`canonical_model_id` for the three DeepSeek flash rows from
`deepseek/deepseek-v4.1-flash` to `deepseek/deepseek-v4.1-flash-1017`, so
`seed render` refused the bundle. The spec header states `base_model` is a
legacy canonical join that must agree with upstream `canonical_model_id`, so
the three dated joins move with upstream; family grouping is unchanged and
`deepseek-v4-pro` already agreed.

Re-lock also drops four lock rows the spec no longer references
(openai.gpt-6-luna, openai.gpt-6-sol, openai.gpt-6.1-sol, zai.glm-5.3-flashx).
They were never rendered: the spec's openai block lists only the 5.5/5.6
family and the shipped bundle carried 7 openai rows, so no user saw a gpt-6
row.

Bundle changes are the projected Models.dev refresh and nothing else:
- deepseek rows: `DeepSeek V4.1 Flash 1017` name/description, release_date
  2026-10-17, context 1000000 -> 1048576
- minimax/MiniMax-M2.7* : status deprecated
- MiniMax-M3: output 512000 -> 524288, structured_output false
- arcee/trinity-large-thinking: output 262144 -> 80000 (shadowed in product
  by the deliberate max_output 262144 correction)
- stepfun rows: cost/family/structured_output refresh
- xai/grok-4.3, grok-4.5: xhigh added to reasoning_options
- zai/GLM-5.2: toggle option
- several rows gain canonical_model_id (now including xiaomi-mimo, moonshot,
  stepfun, zai GLM-5-Turbo)
- openrouter/z-ai/glm-5.3-flash: output 131072 -> 943718

Two tests pinned values this refresh moved, and one golden diff was stale:
- catalog::tests::bundled_seed_canonical_entries_use_upstream_keys_and_yield_to_provider_rows
  asserted xiaomi-mimo rows carry no canonical join; upstream now states the
  join on the provider row, and the provider row still wins on every fact.
- model_reference::tests::bundled_database_is_nonempty_and_honest pinned the
  DeepSeek context at 1000000; the bundle now states 1048576.
- providers-export.golden.json regenerated via WRITE_GOLDEN=1 (not hand
  edited); the diff is exactly the deepseek flash canonical retarget plus the
  new upstream joins, no default changed.

Verified: `cargo test -p codewhale-config -p codewhale-models` 806+9+42+1
passed, 0 failed; `cargo test -p codewhale-tui --lib -- models_dev` 21 passed,
`-- provider_lake` 38 passed, 0 failed; `seed render --check` ok;
`defaults audit` 10 defaults newest stable row, 0 stale.
This commit is contained in:
CodeWhale Bot committed 2026-10-23 06:18:32 -07:00
1 parent efa98bc5c5
commit a339ccb6e7
6 files changed
+193 -484
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

crates/config/assets/models_dev.bundled.json
+90 -66
View File
@@ -9,7 +9,7 @@
"default_rows": "Each provider's `default: true` wire id equals that provider's built-in DEFAULT_*_MODEL so RouteResolver::new() and the descriptor stay in agreement when offline.",
"pending_release_metadata": "GLM-5.3 is live on the Z.ai Coding Plan (docs.z.ai/devpack/overview and docs.z.ai/devpack/latest-model, recorded 2026-08-13) and is the default direct Z.ai model (DEFAULT_ZAI_MODEL); explicit GLM-5.2 selections keep their own id. First-party wire id is GLM-5.3; OpenRouter mirror is z-ai/glm-5.3. Capability/limit/dialect values still inherit from GLM-5.2 until Z.ai publishes distinct 5.3 numbers. Pricing stays absent: Coding Plan publishes credit multipliers, not a USD PAYG row we can stand behind. Z.ai may auto-route GLM-5.2/GLM-5.1 requests to GLM-5.3 on their side; Codewhale still sends the selected picker id. Do not send a [1m] suffix. Scope stays first-party Z.ai plus the OpenRouter mirror; add third-party gateway rows only against that gateway's own published roster.",
"generated_by": "python3 scripts/catalog_models_dev.py seed render from scripts/catalog/models_dev_seed.toml and scripts/catalog/models_dev_seed.lock.json. Do not edit this file by hand; see docs/CATALOG_REFRESH.md.",
"upstream": "https://models.dev/catalog.json fetched 2026-10-17T09:08:34Z sha256 1fc50db52d13d5c9ac1724212b318c221d6f6fc79541b3178851e0db6d058921",
"upstream": "https://models.dev/catalog.json fetched 2026-10-23T13:02:22Z sha256 be32be99493b3bb63f103235e67509b0153d92429675d0f532c96531d5b5d2f9",
"coverage": "21 providers, 96 provider model rows, 4 canonical model entries."
},
"models": {
@@ -18,12 +18,11 @@
"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": "2026-08-12",
"release_date": "2026-08-13",
"last_updated": "2026-08-22",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -139,7 +138,6 @@
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -762,7 +760,7 @@
"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": "2026-08-12",
"release_date": "2026-08-13",
"last_updated": "2026-08-22",
"attachment": false,
"reasoning": true,
@@ -795,7 +793,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -807,14 +805,14 @@
},
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"base_model": "deepseek/deepseek-v4.1-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash",
"base_model": "deepseek/deepseek-v4.1-flash-1017",
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
"name": "DeepSeek V4 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"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": "2026-09-10",
"last_updated": "2026-09-10",
"release_date": "2026-10-17",
"last_updated": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -847,7 +845,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -860,14 +858,14 @@
},
"deepseek-v4-flash-vision-exp": {
"id": "deepseek-v4-flash-vision-exp",
"base_model": "deepseek/deepseek-v4.1-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash",
"base_model": "deepseek/deepseek-v4.1-flash-1017",
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
"name": "DeepSeek V4 Flash Vision Exp",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"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": "2026-09-10",
"last_updated": "2026-09-10",
"release_date": "2026-10-17",
"last_updated": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -900,7 +898,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -913,14 +911,14 @@
},
"deepseek-flash": {
"id": "deepseek-flash",
"base_model": "deepseek/deepseek-v4.1-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"base_model": "deepseek/deepseek-v4.1-flash-1017",
"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": "2026-09-10",
"last_updated": "2026-09-10",
"release_date": "2026-10-17",
"last_updated": "2026-10-17",
"default": true,
"attachment": true,
"reasoning": true,
@@ -954,7 +952,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -988,6 +986,9 @@
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
@@ -1161,6 +1162,7 @@
},
"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",
@@ -1340,12 +1342,13 @@
},
"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": "2026-04-21",
"last_updated": "2026-04-21",
"release_date": "2026-04-20",
"last_updated": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -1358,7 +1361,7 @@
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"temperature": false,
"open_weights": true,
"modalities": {
"input": [
@@ -1407,6 +1410,7 @@
}
],
"tool_call": true,
"structured_output": false,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -1421,7 +1425,7 @@
},
"limit": {
"context": 1000000,
"output": 512000
"output": 524288
},
"cost": {
"input": 0.3,
@@ -1475,7 +1479,8 @@
"output": 1.2,
"cache_read": 0.06,
"cache_write": 0.375
}
},
"status": "deprecated"
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
@@ -1507,7 +1512,8 @@
"output": 2.4,
"cache_read": 0.06,
"cache_write": 0.375
}
},
"status": "deprecated"
}
}
},
@@ -1536,6 +1542,7 @@
}
],
"tool_call": true,
"structured_output": false,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -1550,7 +1557,7 @@
},
"limit": {
"context": 1000000,
"output": 512000
"output": 524288
},
"cost": {
"input": 0.3,
@@ -1604,7 +1611,8 @@
"output": 1.2,
"cache_read": 0.06,
"cache_write": 0.375
}
},
"status": "deprecated"
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
@@ -1636,7 +1644,8 @@
"output": 2.4,
"cache_read": 0.06,
"cache_write": 0.375
}
},
"status": "deprecated"
}
}
},
@@ -4356,9 +4365,9 @@
"output": 384000
},
"cost": {
"input": 0.2088,
"output": 0.4176,
"cache_read": 0.0174
"input": 0.95526,
"output": 1.91052,
"cache_read": 0.079605
}
},
"deepseek/deepseek-v4-flash": {
@@ -4595,8 +4604,8 @@
"output": 235929
},
"cost": {
"input": 0.15,
"output": 1,
"input": 0.1,
"output": 0.95,
"cache_read": 0.05
}
},
@@ -4737,9 +4746,9 @@
"output": 943718
},
"cost": {
"input": 0.62,
"output": 2.42,
"cache_read": 0.14
"input": 0.0341,
"output": 7,
"cache_read": 0.033
}
},
"z-ai/glm-5.3": {
@@ -4780,7 +4789,7 @@
},
"cost": {
"input": 0.079,
"output": 4.8,
"output": 1.4,
"cache_read": 0.078
}
},
@@ -4820,12 +4829,12 @@
},
"limit": {
"context": 1048576,
"output": 131072
"output": 943718
},
"cost": {
"input": 0.0341,
"output": 0.4182,
"cache_read": 0.0109
"input": 0.0052,
"output": 0.1985,
"cache_read": 0.0052
}
},
"dots-studio/dots-3-note-preview:free": {
@@ -4861,7 +4870,8 @@
"cost": {
"input": 0,
"output": 0
}
},
"status": "deprecated"
}
}
},
@@ -5196,7 +5206,7 @@
},
"limit": {
"context": 262144,
"output": 262144
"output": 80000
},
"cost": {
"input": 0.25,
@@ -5375,7 +5385,8 @@
"values": [
"low",
"medium",
"high"
"high",
"xhigh"
]
}
],
@@ -5435,7 +5446,8 @@
"none",
"low",
"medium",
"high"
"high",
"xhigh"
]
}
],
@@ -5493,6 +5505,7 @@
"models": {
"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",
@@ -5510,6 +5523,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -5535,6 +5549,7 @@
},
"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",
@@ -5551,6 +5566,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -5588,11 +5604,13 @@
"models": {
"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": "2026-06-15",
"last_updated": "2026-02-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
@@ -5608,6 +5626,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -5624,15 +5643,17 @@
"output": 256000
},
"cost": {
"input": 0.1,
"output": 0.3,
"cache_read": 0.02
"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",
@@ -5651,6 +5672,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -5667,9 +5689,9 @@
"output": 256000
},
"cost": {
"input": 0.1,
"output": 0.3,
"cache_read": 0.02
"input": 0.10461,
"output": 0.31384,
"cache_read": 0.02092
}
},
"step-3.7-flash": {
@@ -5679,7 +5701,7 @@
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"knowledge": "2026-03-01",
"release_date": "2026-05-29",
"last_updated": "2026-06-29",
"last_updated": "2026-05-29",
"default": true,
"attachment": true,
"reasoning": true,
@@ -5697,6 +5719,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -5715,9 +5738,9 @@
"output": 256000
},
"cost": {
"input": 0.185,
"output": 1.11,
"cache_read": 0.037
"input": 0.20175,
"output": 1.21052,
"cache_read": 0.04035
}
},
"step-5-preview": {
@@ -5744,7 +5767,8 @@
},
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"open_weights": true,
"modalities": {
"input": [
"text",
@@ -5761,9 +5785,9 @@
"output": 65536
},
"cost": {
"input": 0.959,
"output": 2.741,
"cache_read": 0.048
"input": 1.04613,
"output": 2.98895,
"cache_read": 0.10461
}
}
}
crates/config/src/catalog/tests.rs
+3 -2
View File
@@ -876,8 +876,9 @@ fn bundled_seed_canonical_entries_use_upstream_keys_and_yield_to_provider_rows()
for model in ["mimo-v2.6-pro", "mimo-v2.6-flash"] {
let row = find(&rows, "xiaomi-mimo", model);
assert_eq!(
row.canonical_model, None,
"{model} comes from the provider row"
row.canonical_model.as_deref(),
Some(format!("xiaomi/{model}").as_str()),
"{model} keeps the canonical join upstream now states on the provider row"
);
// The text-only hold is gone (#6396): upstream lists image input,
// and a wrong claim costs one rejected, retried request.
crates/config/src/model_reference.rs
+1 -1
View File
@@ -542,7 +542,7 @@ mod tests {
let deepseek = db
.find("deepseek", "deepseek-v4-pro")
.expect("bundled deepseek row");
assert_eq!(deepseek.context_window, Some(1_000_000));
assert_eq!(deepseek.context_window, Some(1_048_576));
assert_eq!(deepseek.modality, Modality::Text);
assert_eq!(deepseek.price_label(), "unknown");
crates/config/src/route/providers-export.golden.json
+14 -8
View File
@@ -217,16 +217,16 @@
"models": [
{
"id": "deepseek-flash",
"canonical": "deepseek/deepseek-v4.1-flash",
"canonical": "deepseek/deepseek-v4.1-flash-1017",
"default": true
},
{
"id": "deepseek-v4-flash",
"canonical": "deepseek/deepseek-v4.1-flash"
"canonical": "deepseek/deepseek-v4.1-flash-1017"
},
{
"id": "deepseek-v4-flash-vision-exp",
"canonical": "deepseek/deepseek-v4.1-flash"
"canonical": "deepseek/deepseek-v4.1-flash-1017"
},
{
"id": "deepseek-v4-pro",
@@ -705,7 +705,8 @@
],
"models": [
{
"id": "kimi-k2.6"
"id": "kimi-k2.6",
"canonical": "moonshotai/kimi-k2.6"
},
{
"id": "kimi-k2.7-code",
@@ -1136,10 +1137,12 @@
],
"models": [
{
"id": "step-3.5-flash"
"id": "step-3.5-flash",
"canonical": "stepfun/step-3.5-flash"
},
{
"id": "step-3.5-flash-2603"
"id": "step-3.5-flash-2603",
"canonical": "stepfun/step-3.5-flash-2603"
},
{
"id": "step-3.7-flash",
@@ -1320,10 +1323,12 @@
],
"models": [
{
"id": "mimo-v2.6-flash"
"id": "mimo-v2.6-flash",
"canonical": "xiaomi/mimo-v2.6-flash"
},
{
"id": "mimo-v2.6-pro",
"canonical": "xiaomi/mimo-v2.6-pro",
"default": true
}
],
@@ -1350,7 +1355,8 @@
],
"models": [
{
"id": "GLM-5-Turbo"
"id": "GLM-5-Turbo",
"canonical": "zhipuai/glm-5-turbo"
},
{
"id": "GLM-5.2",
scripts/catalog/models_dev_seed.lock.json
+82 -404
View File
@@ -1,8 +1,8 @@
{
"source": {
"url": "https://models.dev/catalog.json",
"fetched_at": "2026-10-17T09:08:34Z",
"sha256": "1fc50db52d13d5c9ac1724212b318c221d6f6fc79541b3178851e0db6d058921"
"fetched_at": "2026-10-23T13:02:22Z",
"sha256": "be32be99493b3bb63f103235e67509b0153d92429675d0f532c96531d5b5d2f9"
},
"models": {
"deepseek/deepseek-v4-pro-0813": {
@@ -10,12 +10,11 @@
"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": "2026-08-12",
"release_date": "2026-08-13",
"last_updated": "2026-08-22",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -131,7 +130,6 @@
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -1702,7 +1700,7 @@
},
"limit": {
"context": 262144,
"output": 262144
"output": 80000
},
"cost": {
"input": 0.25,
@@ -1715,13 +1713,13 @@
"deepseek": {
"deepseek-flash": {
"id": "deepseek-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"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": "2026-09-10",
"last_updated": "2026-09-10",
"release_date": "2026-10-17",
"last_updated": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -1754,7 +1752,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -1766,13 +1764,13 @@
},
"deepseek-v4-flash": {
"id": "deepseek-v4-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
"name": "DeepSeek V4 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"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": "2026-09-10",
"last_updated": "2026-09-10",
"release_date": "2026-10-17",
"last_updated": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -1805,7 +1803,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -1818,13 +1816,13 @@
},
"deepseek-v4-flash-vision-exp": {
"id": "deepseek-v4-flash-vision-exp",
"canonical_model_id": "deepseek/deepseek-v4.1-flash",
"canonical_model_id": "deepseek/deepseek-v4.1-flash-1017",
"name": "DeepSeek V4 Flash Vision Exp",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"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": "2026-09-10",
"last_updated": "2026-09-10",
"release_date": "2026-10-17",
"last_updated": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -1857,7 +1855,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -1874,7 +1872,7 @@
"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": "2026-08-12",
"release_date": "2026-08-13",
"last_updated": "2026-08-22",
"attachment": false,
"reasoning": true,
@@ -1907,7 +1905,7 @@
]
},
"limit": {
"context": 1000000,
"context": 1048576,
"output": 393216
},
"cost": {
@@ -2240,7 +2238,8 @@
"output": 1.2,
"cache_read": 0.06,
"cache_write": 0.375
}
},
"status": "deprecated"
},
"MiniMax-M2.7-highspeed": {
"id": "MiniMax-M2.7-highspeed",
@@ -2272,7 +2271,8 @@
"output": 2.4,
"cache_read": 0.06,
"cache_write": 0.375
}
},
"status": "deprecated"
},
"MiniMax-M3": {
"id": "MiniMax-M3",
@@ -2289,6 +2289,7 @@
}
],
"tool_call": true,
"structured_output": false,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -2303,7 +2304,7 @@
},
"limit": {
"context": 1000000,
"output": 512000
"output": 524288
},
"cost": {
"input": 0.3,
@@ -2331,12 +2332,13 @@
"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": "2026-04-21",
"last_updated": "2026-04-21",
"release_date": "2026-04-20",
"last_updated": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -2349,7 +2351,7 @@
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"temperature": false,
"open_weights": true,
"modalities": {
"input": [
@@ -3125,300 +3127,6 @@
}
}
}
},
"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"
}
}
}
}
}
}
},
"openrouter": {
@@ -3509,9 +3217,9 @@
"output": 384000
},
"cost": {
"input": 0.2088,
"output": 0.4176,
"cache_read": 0.0174
"input": 0.95526,
"output": 1.91052,
"cache_read": 0.079605
}
},
"dots-studio/dots-3-note-preview:free": {
@@ -3547,7 +3255,8 @@
"cost": {
"input": 0,
"output": 0
}
},
"status": "deprecated"
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
@@ -3622,8 +3331,8 @@
"output": 235929
},
"cost": {
"input": 0.15,
"output": 1,
"input": 0.1,
"output": 0.95,
"cache_read": 0.05
}
},
@@ -3878,9 +3587,9 @@
"output": 943718
},
"cost": {
"input": 0.62,
"output": 2.42,
"cache_read": 0.14
"input": 0.0341,
"output": 7,
"cache_read": 0.033
}
},
"z-ai/glm-5.3": {
@@ -3921,7 +3630,7 @@
},
"cost": {
"input": 0.079,
"output": 4.8,
"output": 1.4,
"cache_read": 0.078
}
},
@@ -3961,12 +3670,12 @@
},
"limit": {
"context": 1048576,
"output": 131072
"output": 943718
},
"cost": {
"input": 0.0341,
"output": 0.4182,
"cache_read": 0.0109
"input": 0.0052,
"output": 0.1985,
"cache_read": 0.0052
}
}
},
@@ -4061,11 +3770,13 @@
"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": "2026-06-15",
"last_updated": "2026-02-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
@@ -4081,6 +3792,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -4097,15 +3809,17 @@
"output": 256000
},
"cost": {
"input": 0.1,
"output": 0.3,
"cache_read": 0.02
"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",
@@ -4124,6 +3838,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -4140,9 +3855,9 @@
"output": 256000
},
"cost": {
"input": 0.1,
"output": 0.3,
"cache_read": 0.02
"input": 0.10461,
"output": 0.31384,
"cache_read": 0.02092
}
},
"step-3.7-flash": {
@@ -4152,7 +3867,7 @@
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"knowledge": "2026-03-01",
"release_date": "2026-05-29",
"last_updated": "2026-06-29",
"last_updated": "2026-05-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
@@ -4169,6 +3884,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -4187,9 +3903,9 @@
"output": 256000
},
"cost": {
"input": 0.185,
"output": 1.11,
"cache_read": 0.037
"input": 0.20175,
"output": 1.21052,
"cache_read": 0.04035
}
},
"step-5-preview": {
@@ -4216,7 +3932,8 @@
},
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"open_weights": true,
"modalities": {
"input": [
"text",
@@ -4233,9 +3950,9 @@
"output": 65536
},
"cost": {
"input": 0.959,
"output": 2.741,
"cache_read": 0.048
"input": 1.04613,
"output": 2.98895,
"cache_read": 0.10461
}
}
},
@@ -4256,7 +3973,8 @@
"none",
"low",
"medium",
"high"
"high",
"xhigh"
]
}
],
@@ -4316,7 +4034,8 @@
"values": [
"low",
"medium",
"high"
"high",
"xhigh"
]
}
],
@@ -4488,6 +4207,7 @@
"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",
@@ -4504,6 +4224,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -4529,6 +4250,7 @@
},
"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",
@@ -4545,6 +4267,7 @@
"field": "reasoning_content"
},
"tool_call": true,
"structured_output": true,
"temperature": true,
"open_weights": true,
"modalities": {
@@ -4572,6 +4295,7 @@
"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",
@@ -4662,6 +4386,9 @@
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
@@ -4790,55 +4517,6 @@
"cache_read": 0.03,
"cache_write": 0
}
},
"glm-5.3-flashx": {
"id": "glm-5.3-flashx",
"canonical_model_id": "zhipuai/glm-5.3-flash",
"name": "GLM-5.3-FlashX",
"description": "High-speed GLM-5.3-Flash serving option for coding and agent workflows",
"family": "glm-flash",
"release_date": "2026-09-18",
"last_updated": "2026-09-18",
"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": 0.37,
"output": 1.25,
"cache_read": 0.075,
"cache_write": 0
}
}
}
}
scripts/catalog/models_dev_seed.toml
+3 -3
View File
@@ -55,9 +55,9 @@ env = ["DEEPSEEK_API_KEY"]
default = "deepseek-flash"
models = [
{ id = "deepseek-v4-pro", base_model = "deepseek/deepseek-v4-pro-0813" },
{ id = "deepseek-v4-flash", base_model = "deepseek/deepseek-v4.1-flash" },
{ id = "deepseek-v4-flash-vision-exp", base_model = "deepseek/deepseek-v4.1-flash" },
{ id = "deepseek-flash", base_model = "deepseek/deepseek-v4.1-flash" },
{ id = "deepseek-v4-flash", base_model = "deepseek/deepseek-v4.1-flash-1017" },
{ id = "deepseek-v4-flash-vision-exp", base_model = "deepseek/deepseek-v4.1-flash-1017" },
{ id = "deepseek-flash", base_model = "deepseek/deepseek-v4.1-flash-1017" },
]
[[providers]]