Anthropic: Claude Fable 5.2
anthropic/claude-fable-5.2
Claude Fable 5.2 is Anthropic's flagship and ranks #29 of 270 on the TryAii Score, 0.8 points behind Claude Opus 4.8 (batch). It tops the board outright on AA-Omniscience. It costs $8/$40 per million input/output tokens, though similar scores now sell for about $6 per million output tokens and it's among the fastest models we track, at roughly 68-105 tokens/sec.
Prompt $/1M
$8.000
Completion $/1M
$40.000
Context
1,000,000 tok
Best provider
169 tok/s · Anthropic
Specs
- Model id
- anthropic/claude-fable-5.2
- Display name
- Anthropic: Claude Fable 5.2
- Modality
- text+image+file->text
- Tokenizer
- Claude
- Instruct type
- —
- Context length
- 1,000,000
- Max completion
- 128,000
- Prompt $/1M
- $8.000
- Completion $/1M
- $40.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedyes
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Anthropicfastest | 169 |
| 84 | |
| Azure | 70 |
| Amazon Bedrock | 62 |
Prompt caching by provider
All models →| Platform | Caches? | Min tokens | Lifetimes | Resets | Read $/1M | Write $/1M |
|---|---|---|---|---|---|---|
| Yes, on request | 512 | 5 min—1 hour— | unknown | $0.22 | 5 min $11 1 hour $17.6 | |
| Yes, on request | 512 | 5 min—1 hour— | yes | $0.2 | 5 min $10 1 hour $16 | |
| Yes, on request | 512 | 5 min—1 hour— | yes | $0.22 | 5 min $11 1 hour $17.6 | |
| Yes, on request | 512 | 5 min—1 hour— | yes | $0.2 | 5 min $10 1 hour $16 |
- exact
- the provider promises this lifetime
- at least
- promised for at least this long
- not promised
- no guarantee from the provider
We measure these daily and do our best to keep them accurate. Always confirm with the provider’s official documentation.
Official docs: AWS BedrockAzureVertex AIAnthropic
Spot a wrong number? Message our support.