claude-haiku-5-5
Auto-routeranthropic/claude-haiku-5-5
Context
1M
Max output
128K
Input / 1M
$0.10
Output / 1M
$0.50
Cached / 1M
$0.01
Cutoff
Jun 2026
About this model
Claude Haiku 5.5 is Anthropic's fastest model, for high-volume, latency-sensitive tasks such as classification, extraction, and routing. 1M token context window, 128K max output, adaptive thinking with default effort medium. Prices shown are for prompts up to 100,000 tokens; prompts over 100,000 tokens are billed at $0.50 input / $2.50 output / $0.05 cache read per MTok.
Best suited for
- High-volume classification
- Information extraction
- Request routing
- Latency-sensitive production workloads
Built-in tools
Hosted by the gateway — enable them per request without wiring your own endpoint.
Capabilities
Vision
Accepts images alongside text in the same message.
Tools
Native function calling, so agents can invoke your endpoints.
System prompt
Honours a dedicated system role, separate from the user turn.
Supported parameters
max_tokensThe maximum number of tokens to generate before stopping.
stop_sequencesCustom text sequences that will cause the model to stop generating.
streamSends the response in real-time as it is being generated.
tool_choiceDecides whether to use tools or just the model for generating responses.
toolsLists tool definitions or capabilities available to the model.
response_typeUse this model
OpenAI-SDK compatible, with gateway fallback and routing across providers.
Other Anthropic models
| Model | Context | Max output | Input | Output | Capabilities |
|---|---|---|---|---|---|
| claude-sonnet-5-5 Chat | 1M | 128K | $2.00 | $10.00 | Vision, Tools, System prompt |
| claude-opus-5-5 Chat | 1M | 128K | $4.00 | $20.00 | Vision, Tools, System prompt |
| claude-fable-5-1 Chat | 1M | 128K | $10.00 | $50.00 | Vision, Files, Tools, System prompt, Reasoning |
| claude-sonnet-5 Chat | 1M | 128K | $2.00 | $10.00 | Vision, Tools, System prompt |
| claude-opus-5 Chat | 1M | 128K | $5.00 | $25.00 | Vision, Tools, System prompt |
| claude-fable-5 Chat | 1M | 128K | $10.00 | $50.00 | Vision, Tools, System prompt |
| claude-opus-4-8 Chat | 1M | 128K | $5.00 | $25.00 | Vision, Files, Tools, System prompt, Reasoning |
| claude-opus-4-7 Chat | 1M | 128K | $5.00 | $25.00 | Vision, Files, Tools, System prompt, Reasoning |
| claude-sonnet-4-6 Chat | 1M | 128K | $3.00 | $15.00 | Vision, Files, Tools, System prompt |
| claude-opus-4-6 Chat | 1M | 128K | $5.00 | $25.00 | Vision, Files, Tools, System prompt |
| claude-opus-4-5-20251101 Chat | 200K | 64K | $5.00 | $25.00 | Vision, Files, Tools, System prompt |
| claude-haiku-4-5-20251001 Chat | 200K | 64K | $1.00 | $5.00 | Vision, Files, Tools, System prompt |
Pricing & provider details
Anthropic
anthropic/claude-haiku-5-5
- Input · per 1M
- $0.10
- Output · per 1M
- $0.50
- Cached input · per 1M
- $0.01
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Knowledge cutoff
- Jun 2026
- Auto-router
- Supported
Start building today
Route claude-haiku-5-5 — and every other model in the catalogue — through one endpoint, with failover built in.