Claude Fable 5
✓ VERIFIED BY ANTHROPICAnthropic · Proprietary · Released Jun 9, 2026 · anthropic/claude-fable-5
Best $10.00 in / $50.00 out via Anthropic
1M contextVisionToolsReasoningStructured outputPrompt caching
Available from 8 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 3 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 CheaperInferenceDIRECTMARKETPLACE | $6.50 | $32.50 | — | — | — | — | — | — |
| CheaperInferenceDIRECTMARKETPLACE | $7.50 | $37.50 | — | — | — | — | — | — |
 Anthropic1ST PARTY | $10.00 | $50.00 | $1.00 | 1M | — | ✕ | ✕ | 100.0% |
 Amazon Bedrock | $10.00 | $50.00 | $1.00 | 1M | — | ✕ | ✕ | — |
 Azure | $10.00 | $50.00 | $1.00 | 1M | — | 3.5s | 133 tok/s | 100.0% |
 Google | $10.00 | $50.00 | $1.00 | 1M | — | 2.1s | 131 tok/s | — |
 Claude Platform on AWS | $10.00 | $50.00 | $1.00 | 1M | — | ✕ | ✕ | 100.0% |
| Google | $11.00 | $55.00 | $1.10 | 1M | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 3 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Quality benchmarksCURATED AUG 24, 2026
GPQA Diamond93.18%INDEPENDENTVals: refusal-triggered fallbacks counted as successes; 55.6% if refusals count as failures (41.9% refusal rate)source ↗ 2026-08-24
Humanity's Last Exam55.5%INDEPENDENTText-only pass@1; max effort, Opus 4.8 fallback configsource ↗ 2026-08-24
Third-party reported results, hand-curated with sources — not measured by ModelIndex. Our own measured serving data (TTFT/TPS/SMOKE) is in the providers table above.
Pricing variants · USD / MTok in / out
STANDARD
$10.00 / $50.00
per MTok in / out
BATCH
$5.00 / $25.00
async batch
CACHE READ $1.00CACHE WRITE $12.50WEB SEARCH $0.01 / searchCACHE WRITE 1H $20.00 / MTok
Recent changesRSS ↗
Sep 23, 2026endpoint added · cheaperinference6 → 7
About
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
Specifications
Context window1,000,000
Max output128,000
Modalities intext, image, file
Modalities outtext
LicenseProprietary
ReleasedJun 9, 2026
TokenizerClaude
Related
Embed badge
[](https://modelindex.ai/models/anthropic/claude-fable-5)Sources
anthropic ↗23 minutes ago
OFFICIAL PRICINGOpenRouter API23 minutes ago
AGGREGATORLiteLLM dataset23 minutes ago
AGGREGATORModelIndex benchmarks3 days ago
MEASURED✓ Verified against Anthropic’s own source.
Verified 23 minutes ago · list prices, not negotiated rates.