Claude Haiku 5.5

Anthropic Claude Haiku 5.5 — 最快最省, 适合分类、抽取、路由等高并发低延迟任务。1M 上下文 · 128K 输出 · Adaptive thinking(默认 effort=medium) · 提示超过 10 万 token 按长上下文价。

Model ID: claude-haiku-5-5 · Type: chat · Provider: Anthropic

Endpoints: /v1/messages · /v1/chat/completions · /v1/responses

Pricing

Input (per 1M tokens)$0.1 USD
Output (per 1M tokens)$0.5 USD
Cache read (per 1M tokens)$0.01 USD
Cache write 5m (per 1M tokens)$0.125 USD

Context tiers

≤ 100000 tokens$0.1 / 1M in$0.5 / 1M out
> 100000$0.5 / 1M in$2.5 / 1M out
from openai import OpenAI

client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="claude-haiku-5-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does Claude Haiku 5.5 cost on 370.AI?

Claude Haiku 5.5 (`claude-haiku-5-5`) is billed per usage at $0.1/1M in · $0.5/1M out, in USD. Current pricing is always listed at https://370.ai/models/claude-haiku-5-5.

How do I call Claude Haiku 5.5 through 370.AI?

Send a request to https://api.router.ai/v1/v1/messages with the header `Authorization: Bearer <your API key>` and `"model": "claude-haiku-5-5"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does Claude Haiku 5.5 support?

Claude Haiku 5.5 can be called on: /v1/messages; /v1/chat/completions; /v1/responses.

What is Claude Haiku 5.5's context window?

Claude Haiku 5.5 accepts up to 1,000,000 input tokens and can return up to 128,000 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can Claude Haiku 5.5 do?

Claude Haiku 5.5 supports: vision, function_calling, prompt_caching.

Who makes Claude Haiku 5.5?

Claude Haiku 5.5 is a chat model from Anthropic, available through the 370.AI gateway with the same API key as every other model.

Call it through the 370.AI OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can browse the catalog and call any text model through MCP (https://mcp.router.ai/mcp); for image, video and other modalities use the API above.

Which should you pick

API reference · All models