Quick answer
Claude Fable 5, Opus 5, and Sonnet 5 list a 1,000,000 tokens context window and 128,000 tokens maximum output. Claude Haiku 4.5 has a smaller documented context window.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| Claude Fable 5, Opus 5, and Sonnet 5 contextAPI model specification; model availability can differ by provider. | 1,000,000 tokens | Claude 5 family | AnthropicAug 22, 2026 |
| Claude 5 family maximum outputSeparate maximum output for the listed Claude 5 API models. | 128,000 tokens | Claude 5 family | AnthropicAug 22, 2026 |
| Claude Haiku 4.5 contextModel-specific API context window. | 200,000 tokens | Claude Haiku 4.5 | AnthropicAug 22, 2026 |
Why does this limit matter?
Context and output are different budgets, and applications must reserve room for the response they request.
Provider and model availability can affect which documented specification is relevant to a deployed endpoint.
What should you check?
- Read the model ID from the request or deployment configuration.
- Match it to the current Anthropic models table.
- Add instructions, messages, tools, retrieved documents, and expected output before comparing the total.
Important caveats
- This page covers API model specifications, not consumer claude.ai usage allowances.
- Pinned snapshots and aliases can point to different lifecycle states; record the exact model ID.
HyperObserve reports the documented platform constraint. Your application, SDK, gateway, provider, region, or account can impose a lower effective limit.
Related