Model detail
Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window. It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.
Model specs
- Model ID
-
claude-haiku-5-5
- Context length
- 1M
- Max output
- 128K
- I/O modalities
- Released
- 2026-10
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
Anthropic Messages
/v1/messagesPOST -
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /1M Tokens
| Tier | Input /1M Tokens | Output /1M Tokens | Cache read /1M Tokens | Cache write /1M Tokens |
|---|---|---|---|---|
| standard Length ≤ 100K | $0.1000 | $0.5000 | $0.0100 | $0.1250 |
| long_context Length > 100K | $0.5000 | $2.5000 | $0.0500 | $0.6250 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Anthropic model for high-volume, latency-sensitive classification, extraction, routing
Claude Haiku 5.5 is an Anthropic model for high-volume, latency-sensitive classification, extraction, routing, and focused subagent work, with adaptive reasoning and text/image input.
What should you check before using it?
1,000,000 context, 128,000 output tokens
Claude Haiku 5.5 supports reasoning, tool calling, structured output, streaming, prompt caching, vision input and the OpenAI SDK. Knowledge cutoff: 2026-06. Released 2026-10-07.
Why use it through MixRoute?
Claude Haiku 5.5 cache reads cut repeated-prompt cost
Cached prefixes are billed at $0.0100 per 1M tokens for inputs up to 100,000 tokens (standard input $0.1000); above that, $0.0500 and $0.5000 respectively, so repeated system prompts cost less. MixRoute serves Claude Haiku 5.5 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID claude-haiku-5-5 and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
Claude Haiku 5.5 supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
Claude Haiku 5.5 can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
Claude Haiku 5.5 supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
Claude Haiku 5.5 supports prompt caching under supported routing conditions.
Vision input
Claude Haiku 5.5 can process image inputs alongside text.
image_url content part alongside text messages.
OpenAI SDK
Call Claude Haiku 5.5 through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
Reasoning tokens are billed as output on Claude Haiku 5.5, at $0.50 per 1,000,000 token. They are generated before the visible answer and count toward both latency and spend, so a higher reasoning setting costs more even when the final answer is short.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.