Claude model for demanding reasoning and long-horizon agentic work
Claude Fable 5.1 by anthropic is offered by 42 providers on this page. Public prices are shown for 41 of them. Its official list price is $10.00 per 1M input tokens and $50.00 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 1.3× across the providers that host it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 53.4 on the Intelligence Index, with 81.6 for coding and 57.9 for agentic tasks. Against its lowest blended price of $20.00 per 1M, that is roughly 3 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 71 tokens per second, with 220.12s to the first token. Running one task of the Artificial Analysis suite costs about $7.6297, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 262,144 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2026-06.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| GitLab Duo duo-chat-fable-5-1 | Cloud | Free | $0 | $0 | 1,000,000 | 128,000 | ||
| AnthropicOfficial | First-party | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| NanoGPT anthropic/claude-fable-5.1 | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| NEAR AI Cloud | Gateway | $10.00 | $50.00 | $0.25 | — | 1,000,000 | 128,000 | |
| LLM Gateway | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| LLM Gateway | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| LLM Gateway | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| Kilo Gateway anthropic/claude-fable-5.1 | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| Venice AI | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
| CommandCode | Gateway | $10.00 | $50.00 | $0.25 | $12.50 | 1,000,000 | 128,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 42 providers.
2 / 42 providers expose no reasoning control (reasoning_options: []).
1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.
Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-02). Each future sync adds a point, and once accumulated a line is drawn here.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Terminal-Bench-Science | variant: production safeguards with fallback · v0.1 | 52.6 | score | Source ↗ |
| Terminal-Bench | variant: production safeguards with fallback · v4.0 | 55.8 | score | Source ↗ |
| GDPval-AA | variant: production safeguards with fallback · v2 | 1853 | Elo | Source ↗ |
| OSWorld | variant: production safeguards; interventions score zero; no fallback · dataset: August 2026 task release · v2.0 | 77.9 | partial score | Source ↗ |
| OSWorld | variant: production safeguards; interventions score zero; no fallback · dataset: August 2026 task release · v2.0 | 41.7 | strict success rate | Source ↗ |
| Humanity's Last Exam | variant: without tools; production safeguards with fallback | 60.9 | score | Source ↗ |
| Humanity's Last Exam | variant: with tools; production safeguards with fallback | 65 | score | Source ↗ |
| AutomationBench | variant: production safeguards with fallback | 31.4 | pass rate | Source ↗ |
| CursorBench | variant: max effort; production safeguards with fallback · v3.2.0 | 73.4 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.