Claude Fable 5.1
Claude Fable 5.1 is a proprietary model from Anthropic with a 1M-token context window. 4 providers list it; as of 25 Oct 2026, the cheapest listings (Anthropic and 2 others) charge $10.00 per million input tokens and $50.00 per million output tokens.
Providers serving Claude Fable 5.1
Cheapest first, by the blended rate of three input tokens to one output token. Prices in US dollars per million tokens, checked 25 Oct 2026; the source link opens where the price is published. All 4 list tool calling and JSON mode; none lists an OpenAI-compatible API.
What each provider charges
Blended price per 1M tokens (3 input : 1 output); bars start at $0. Prices checked 25 Oct 2026.
What this shows: the highest listing is 10% above the lowest: $22.00 (Amazon Bedrock) against $20.00 (Anthropic and 2 others).
- Anthropic and 2 others: $20.00 per 1M tokens, blended
- Amazon Bedrock: $22.00 per 1M tokens, blended
How each provider handles your prompts
For each provider's paid API, from its own pages, checked 26 Oct 2026. Where a promise lives matters: a signed agreement binds the provider, while a docs page can change without notice. Not legal advice.
| Provider | Trains on your prompts | Keeps prompts | Zero retention | Data processing agreement |
|---|---|---|---|---|
| Anthropic Flagged content can be kept up to 2 years; Covered Models (Claude Fable 5/5.1, Mythos 5/5.1) require 30-day retention and are excluded from ZDR. Flagged content can be kept up to 2 years; Covered Models (Claude Fable 5/5.1, Mythos 5/5.1) require 30-day retention and are excluded from ZDR.MoreLess | No | Deleted within 30 days | On request | Public |
Google VertexClaude Fable/Mythos keep all traffic 30 days and require sharing it with Anthropic; Google Search grounding keeps queries 3 days; the 24-hour cache can be switched off; the Interactions API stores prompts unless store=false.MoreLess | No | Not stored beyond the request, except a 24-hour cache (on by default) and abuse-flagged prompts (up to 90 days) | Enterprise plans only | Public |
Microsoft AzureApproved 'modified abuse monitoring' turns off the storage and human review; stateful features (Responses API, stored completions, Assistants threads) keep history as you configure them.MoreLess | No | Prompts and outputs flagged by abuse monitoring may be stored for human review; no retention period stated | Enterprise plans only | Public |
Amazon BedrockOpenAI models (flagged traffic) and Claude Fable 5/5.1 (all traffic, with possible AWS human review) keep data up to 30 days; the Responses API stores responses unless store=false.MoreLess | No | Not stored for most models; up to 30 days for abuse detection on models AWS lists | Yes, by default | Public |
Claude Fable 5.1 benchmark scores
Compare every model in Bench rankingsPublished scores only, each linked to its source. Ticks are every other model's best published score.
GPQA Diamond
PhD-level scientific reasoning, pass@1, no tools
max effort, production safeguards on 93.7%, source: Artificial Analysis, max effort, production safeguards onJoint 13th of 221 models with a score
APEX-Agents
Agentic office work, APEX-Agents 1.1, Pass@1 in the maintainers' harness
max effort 68.6%, source: APEX-Agents leaderboard (Mercor), max effortRanks 4th of 48 models with a score
Humanity's Last Exam (text-only)
Reasoning & knowledge, no tools
max effort, production safeguards on 59.1%, source: Artificial Analysis, max effort, production safeguards onRanks 2nd of 221 models with a score
τ³-Banking
Agentic tool use with knowledge retrieval (banking)
max effort, production safeguards on 47.2%, source: Artificial Analysis, max effort, production safeguards onJoint 7th of 103 models with a score
Terminal-Bench 2.1 (Terminus 2)
Agentic coding & terminal use
max effort, production safeguards on 91.4%, source: Artificial Analysis, max effort, production safeguards onRanks 1st of 127 models with a score
CritPt v2
Physics reasoning
72%, source: CritPt v2 leaderboardRanks 7th of 25 models with a score
SciCode (with background)
Scientific coding
max effort, production safeguards on 63.1%, source: Artificial Analysis, max effort, production safeguards onRanks 2nd of 118 models with a score
GDPval-AA v2.1 (Elo)
Real-world work tasks; a rating against other models, not a percentage
max effort, production safeguards on 1755, source: Artificial Analysis, max effort, production safeguards onRanks 5th of 144 models with a score
LCR
Long-context reasoning, AA-LCR v1.1
max effort, production safeguards on 85.3%, source: Artificial Analysis, max effort, production safeguards onRanks 5th of 211 models with a score
Omni Accuracy
Omniscience knowledge accuracy
max effort, production safeguards on 67.2%, source: Artificial Analysis, max effort, production safeguards onRanks 1st of 216 models with a score
Non-Hallucination
1 − hallucination rate
low effort, production safeguards on 34.4%, source: Artificial Analysis, low effort, production safeguards onRanks 91st of 216 models with a score
ITBench
Kubernetes incident root-cause analysis, Artificial Analysis's ITBench-AA
max effort, production safeguards on 49.5%, source: Artificial Analysis, max effort, production safeguards onRanks 6th of 41 models with a score
Each score is the model's best published result across its settings, named beside it. A setting above the default can use more tokens per task, which a per-token price does not show.
Show as table
| Benchmark | Score | Setting |
|---|---|---|
GPQA Diamond PhD-level scientific reasoning, pass@1, no tools | 93.7%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
APEX-Agents Agentic office work, APEX-Agents 1.1, Pass@1 in the maintainers' harness | 68.6%, source: APEX-Agents leaderboard (Mercor), max effort | max effort |
Humanity's Last Exam (text-only) Reasoning & knowledge, no tools | 59.1%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
τ³-Banking Agentic tool use with knowledge retrieval (banking) | 47.2%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
Terminal-Bench 2.1 (Terminus 2) Agentic coding & terminal use | 91.4%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
CritPt v2 Physics reasoning | 72%, source: CritPt v2 leaderboard | Default |
SciCode (with background) Scientific coding | 63.1%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
GDPval-AA v2.1 (Elo) Real-world work tasks; a rating against other models, not a percentage | 1755, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
LCR Long-context reasoning, AA-LCR v1.1 | 85.3%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
Omni Accuracy Omniscience knowledge accuracy | 67.2%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
Non-Hallucination 1 − hallucination rate | 34.4%, source: Artificial Analysis, low effort, production safeguards on | low effort, production safeguards on |
ITBench Kubernetes incident root-cause analysis, Artificial Analysis's ITBench-AA | 49.5%, source: Artificial Analysis, max effort, production safeguards on | max effort, production safeguards on |
More from Anthropic
- Claude Opus 4.7from $5.00 in · 1M · GPQA 91.4% · 7 providers
- Claude Sonnet 4.6from $3.00 in · 1M · GPQA 87.5% · 7 providers
- Claude Fable 5from $10.00 in · 1M · GPQA 92.6% · 6 providers
- Claude Opus 4.8from $5.00 in · 1M · GPQA 92% · 6 providers
- Claude Opus 5from $5.00 in · 1M · GPQA 93.7% · 6 providers
- Claude Sonnet 5from $2.00 in · 1M · GPQA 91.1% · 6 providers
- Claude Haiku 5.5from $0.10 in · 1M · GPQA 89.6% · 4 providers
- Claude Opus 5.5from $4.00 in · 1M · GPQA 90.6% · 4 providers
- Claude Sonnet 5.5from $2.00 in · 1M · GPQA 95.6% · 4 providers
- Claude Mythos 5.1from $10.00 in · 1M · 2 providers
- Claude 4.5 Haiku200k · GPQA 67.2%