Claude Haiku 5.5

NEW

Model ID

Put this value in the request body's `model` field — not the display name above.

Text generationReasoningImage understandingToolsJSON1MClosed source

by Anthropic · Anthropic Haiku 5.5, the new lightweight Claude. 1M context, fast and economical; good for high concurrency, classification, extraction and sub-tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

Try it now

Quick start

EndpointPOST /v1/chat/completions
AuthenticationAuthorization: Bearer sk-gpushare-…Get API key
Call styleSynchronous: one request returns the result
Base URLhttps://qd.zsopc.com/v1
cURL
curl https://qd.zsopc.com/v1/chat/completions \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-5-5",
    "messages": [
      {"role": "user", "content": "你可以帮我做什么"}
    ]
  }'

Pricing

Billed per token: input and output are priced separately and settled on the upstream's reported usage.

Rates
Input 0.0404Credits/K·Output 0.2022Credits/K
  • Input tokens that hit the prompt cache are billed at 4.04 Credits / 1M — cheaper than full-price input.
  • Tokens written into the prompt cache for the first time are billed at 50.55 Credits / 1M — above full-price input. The cache lives about 5 minutes, so it only pays off if you call again within that window.
  • When a turn's prompt exceeds 100,001 tokens, input, cache-hit and output all switch to the long-context rates (input 202.2 Credits / 1M). That is the upstream's whole-turn surcharge for very long requests, passed straight through.
  • Failed requests (upstream 4xx / 5xx) are not billed.
  • All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Sign in and any personal discount on your account will show up here. Sign in

Capabilities & specs

Category
Text generation
Context window
1M tokens
Default max output
128k tokens
Endpoint family
Chat Completions
Protocols
OpenAI Chat · Anthropic Messages
License
Closed source

Try it

Pick a key under "API access" and fire one real request to see the response — the estimated cost is shown before you send.

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ Claude Haiku 5.5→✓ claude-haiku-5-5

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

A request body field is invalid, or this model doesn't support the protocol endpoint you called.

→ Check your request body against the sample code above

Try it

Claude Haiku 5.5 FAQ

How do I call Claude Haiku 5.5?
Set the model field of the request body to claude-haiku-5-5, send it to https://qd.zsopc.com/v1/chat/completions, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. The official OpenAI, Anthropic and Google Gemini SDKs all work directly; just point base_url at this gateway.
How much does the Claude Haiku 5.5 API cost?
  • Input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens
  • Output: 202.2 credits (≈ ¥3.37 / ≈ $0.5) per 1M tokens
  • Cached input: 4.04 credits (≈ ¥0.067 / ≈ $0.01) per 1M tokens
  • Cache write: 50.55 credits (≈ ¥0.842 / ≈ $0.125) per 1M tokens
  • Long-context tier (prompt ≥ 100,001 tokens): input 202.2 credits (≈ ¥3.37 / ≈ $0.5), output 1,011 credits (≈ ¥16.85 / ≈ $2.5)
  • Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.
How large is Claude Haiku 5.5's context window?
1,000,000 tokens, with a default output limit of 128,000 tokens per request.
What can Claude Haiku 5.5 do?
Image input, Tool calling, Thinking mode, JSON mode. Compatible protocols: OpenAI Chat Completions, Anthropic Messages.

Prices and details updated 2026-11-17. Input price is about $0.1 per 1M tokens. Markdown version of this page: /en/models/claude-haiku-5-5.md

Related