mirror of
https://github.com/Heretek-AI/Token-Max.git
synced 2026-10-12 10:19:51 +00:00
John Smith
2dd7a1b34a
- Harmonize plan generation prompt cache rate to shared 75% default from estimate-constants.json - Update TokenTranslator to resolve plan token capacity model-specifically via resolveTierModelBudget - Fix calculatePoolDrain to drain model-specific allowances and eliminate Math.max deflation on low-cost models - Make buildStackCandidates model-aware for accurate Dangerous Dave and Mix & Match stacking - Update WorkflowCalculator to resolve plan capacity model-specifically for active workloads - Reconcile Cursor Pro evidence quotes in throttle-profiles and reasoning token policies - Add unit tests for model-aware stack candidates and pool drainage (102/102 passing)
150 lines
5.5 KiB
JSON
150 lines
5.5 KiB
JSON
{
|
|
"id": "byteplus",
|
|
"name": "BytePlus ModelArk Coding Plan",
|
|
"category": "api-provider",
|
|
"url": "https://www.byteplus.com/en/activity/arkcodingplan",
|
|
"lastVerified": "2026-09-19",
|
|
"tiers": [
|
|
{
|
|
"name": "Lite",
|
|
"monthlyPrice": 10,
|
|
"limits": {
|
|
"usage": "3x the usage of the Claude Pro plan",
|
|
"requests": "≈1,900 requests/5h, 12,000/week, 24,000/month (official docs; older FAQ quoted 1,200/9,000/18,000)",
|
|
"tools": "Claude Code, Cursor, Cline, Kilo Code, Roo Code, OpenCode"
|
|
},
|
|
"models": [
|
|
"Dola-Seed-2.0-Pro",
|
|
"Dola-Seed-2.0-Lite",
|
|
"GLM-5.3-Flash",
|
|
"Dola-Seed-2.0-Code",
|
|
"DeepSeek-V4-Flash",
|
|
"Kimi K2.5",
|
|
"GPT-OSS-120b"
|
|
],
|
|
"estimatedTokenBudget": {
|
|
"description": "3x Claude Pro usage (~36M tokens/mo, anchored to our Claude Pro estimate)",
|
|
"estimatedMillionTokens": 36,
|
|
"assumptions": "BytePlus markets Lite as 3x the Claude Pro quota; anchored to our own Claude Code Pro conservative estimate (12M) = 36M tokens. Official docs publish request quotas (≈1,900/5h, 12,000/week, 24,000/month) but no token conversion",
|
|
"estimateMeta": {
|
|
"sourceUrl": "https://docs.byteplus.com/en/docs/ModelArk/1925114",
|
|
"sourceQuote": "The Lite plan provides a usable total quota equivalent to 3x that of the Claude Pro plan, while the Pro plan offers 5x the quota of the Lite plan",
|
|
"sourceType": "derived",
|
|
"confidence": "medium",
|
|
"verifiedAt": "2026-09-19",
|
|
"basisModel": "Claude Pro conservative estimate (12M)"
|
|
}
|
|
},
|
|
"perModelTokenBudgets": {
|
|
"dola-seed-2.0-pro": {
|
|
"estimatedMillionTokens": 36.0,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"dola-seed-2.0-lite": {
|
|
"estimatedMillionTokens": 123.03,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"glm-5.3-flash": {
|
|
"estimatedMillionTokens": 193.98,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"dola-seed-2.0-code": {
|
|
"estimatedMillionTokens": 45.0,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"deepseek-v4-flash": {
|
|
"estimatedMillionTokens": 121.83,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"kimi k2.5": {
|
|
"estimatedMillionTokens": 25.71,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"gpt-oss-120b": {
|
|
"estimatedMillionTokens": 50.45,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
}
|
|
},
|
|
"notes": "Flexible model selection or Auto mode"
|
|
},
|
|
{
|
|
"name": "Pro",
|
|
"monthlyPrice": 50,
|
|
"limits": {
|
|
"usage": "5x Lite usage (also marketed as 3x Claude Max usage)",
|
|
"requests": "5x Lite quotas (≈9,500/5h, 60,000/week, 120,000/month)",
|
|
"bonus": "ArkClaw included during subscription"
|
|
},
|
|
"models": [
|
|
"Dola-Seed-2.0-Pro",
|
|
"Dola-Seed-2.0-Lite",
|
|
"GLM-5.3-Flash",
|
|
"DeepSeek-V4-Pro",
|
|
"Kimi K2.5",
|
|
"GPT-OSS-120b"
|
|
],
|
|
"estimatedTokenBudget": {
|
|
"description": "5x Lite (~180M tokens/mo)",
|
|
"estimatedMillionTokens": 180,
|
|
"assumptions": "5x the Lite estimate (36M), consistent with the marketed 5x tier multiplier; exact credits unpublished",
|
|
"estimateMeta": {
|
|
"sourceUrl": "https://www.byteplus.com/en/activity/arkcodingplan",
|
|
"sourceType": "research",
|
|
"confidence": "low",
|
|
"verifiedAt": "2026-09-19"
|
|
}
|
|
},
|
|
"perModelTokenBudgets": {
|
|
"dola-seed-2.0-pro": {
|
|
"estimatedMillionTokens": 180.0,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"dola-seed-2.0-lite": {
|
|
"estimatedMillionTokens": 615.15,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"glm-5.3-flash": {
|
|
"estimatedMillionTokens": 969.9,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"deepseek-v4-pro": {
|
|
"estimatedMillionTokens": 90.0,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"kimi k2.5": {
|
|
"estimatedMillionTokens": 128.57,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"gpt-oss-120b": {
|
|
"estimatedMillionTokens": 252.27,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
}
|
|
},
|
|
"notes": "Model availability varies by country/region"
|
|
}
|
|
],
|
|
"gotchas": [
|
|
"2026 refresh renamed models from Bytedance-Seed naming to Dola-Seed-2.0 pro/lite",
|
|
"Quota is marketed as a multiplier of Claude Pro/Max plans, not absolute credits",
|
|
"Non-coding use of the plan may be treated as abuse and can lead to subscription deactivation or account suspension",
|
|
"Model availability varies by region"
|
|
],
|
|
"tosHighlights": [],
|
|
"dataTraining": "No training on Customer Data under BytePlus AI Services terms (except volunteered feedback)",
|
|
"ipIndemnity": false,
|
|
"stackingPolicy": "silent",
|
|
"stackingPolicyNote": "BytePlus AI terms cover data training but contain no multi-account clause; plans are \"primarily intended for individual developers\" and non-coding use may be treated as abuse."
|
|
} |