Compare models
Choose two or three models, including exact thinking and fast versions. Copy the URL to share your selection.
| Comparison | Claude Fable 5.1 Maxanthropic/claude-fable-5-1-max | Choose model 2 |
|---|---|---|
| Type | Chat | — |
| Best for | Hardest reasoning problems where accuracy matters more than speed | — |
| TokenBazaar price | $10.00 in / $50.00 out per 1M tokens | — |
| Cached input / 1M tokens | $0.25 per 1M tokens | — |
| Cache write / 1M tokens | $12.50 per 1M tokens | — |
| Cached output | Not offered · standard output rate applies | — |
| Market price | $10.00 in / $50.00 out per 1M tokens | — |
| Context window (provider) | 1,000,000 tokens | — |
| Input token limit (provider) | Within the context window | — |
| Maximum output | 128,000 tokens | — |
| Knowledge cutoff | Jun 2026 | — |
| Vendor input modalities | Text, Image | — |
| Vendor output modalities | Text | — |
| TokenBazaar endpoints | POST /v1/chat/completions · POST /v1/messages | — |
| TokenBazaar input | Text, Image/PDF content through the chat bridge | — |
| TokenBazaar output | Text | — |
No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenBazaar API support.
— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenBazaar media controls and response formats are listed separately.
Claude Fable 5.1 Max
Sources and verification
Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.
- Provider model specifications
Vendor-reported
Last checked - Anthropic Fable 5.1 system card · sections 8.1–8.11
Vendor-reported
Last checked - CursorBench public evaluation
Third-party report
Last checked - Proximal · FrontierSWE public leaderboard
Third-party report
Last checked - Vals AI · Claude Fable 5.1 evaluation
Third-party report
Last checked - Google Gemini 4 Argon comparison chart
Vendor-reported
Last checked - Cognition · FrontierCode 1.1 original leaderboard
Third-party report
Last checked
Research notes (2)
- Published provider limits; maximum-capacity requests have not been independently exercised through TokenBazaar. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.
- Benchmark configuration is stated per result. Provider max-effort tests are not measurements of the default medium or xhigh catalog versions. ProgramBench 87.6 is the vendor’s filtered 166-task test, not a generic public score.