Standard & Paid Price
The locked value is the exact Paid Price after your first top-up; the discount is derived from the two absolute prices
Unlock with a top-up
| Meter | Standard Price | Paid Price | Save |
|---|---|---|---|
| Input price | $0.1000 / 1M tokens | $0.0600 / 1M tokens | -40% |
| Completion price | $0.5000 / 1M tokens | $0.3000 / 1M tokens | -40% |
| Cache read price | $0.0100 / 1M tokens | $0.0060 / 1M tokens | -40% |
| Cache creation price | $0.1250 / 1M tokens | $0.0750 / 1M tokens | -40% |
| 1h cache creation price | $0.2000 / 1M tokens | $0.1200 / 1M tokens | -40% |
Dynamic pricing · 2 tiers
Billing details
Vendor list price comparison
Description
Anthropic Claude Haiku 5.5 — fast, cost-efficient text and image understanding for classification, extraction, routing, and agents. It has a 1,000,000-token context window and supports up to 128,000 output tokens. Adaptive thinking defaults to medium effort; use output_config.effort in Messages to select low, medium, high, xhigh, or max. Streaming and forced tool calls are supported. Prompts over 100,000 input tokens use the higher rate for the whole request, including output and cache tokens.
Capabilities
- Input modalities
- text, image
- Output modalities
- text
- Tasks
- chat, reasoning, vision
API endpoints
POST /v1/messages(anthropic)POST /v1/chat/completions(openai)