Anthropic
Claude Haiku 5.5
Claude Haiku 5.5 handles short, repeatable tasks such as classification and summarization at high volume.
Model interface
API model ID
claude-haiku-5-5- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions
Best for
- Route support tickets by topic
- Condense a conversation into a handoff note
Technical details
Read the model documentation- API model ID
claude-haiku-5-5- Provider
- Anthropic
- Modality
- Text
- Input
- Chat messages
- Output
- Text
- Endpoint
POST /v1/chat/completions- API constraints
- Use automatic tool selection. Temperature, top_p and schema-based response formats are unavailable.
- Adaptive is the only supported thinking mode.
Request parameters
messagesmax_completion_tokensstreamtoolscache_control
Additional parameters
context_managementmax_tokensparallel_tool_callsreasoning_effortstopstream_optionsthinkingtool_choiceuserweb_search_options
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per 1M input tokens | |
| Base rate | $0.12 |
| prompts over 100,000 tokens | $0.60 |
| Per 1M output tokens | |
| Base rate | $0.60 |
| prompts over 100,000 tokens | $3.00 |
| Per 1M cached input tokens | |
| Base rate | $0.012 |
| prompts over 100,000 tokens | $0.06 |
| Per 1M cache-write tokens | |
| Base rate | $0.15 |
| prompts over 100,000 tokens | $0.75 |
| Per 1K web searches | $12.00 |
Billing notes
- A prompt over 100,000 tokens bills the whole request at the long-context rates.
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue