AAnthropic0.2× of list price
Claude Haiku 5.5
claude-haiku-5-5Anthropic's fastest current model, for high-volume, low-latency work like classification, extraction, and routing. 1M context; prompts over 100K tokens bill the whole request at 5x.
Pricing
USD per million tokens| Type | TokenArmy | List price |
|---|---|---|
| Input | $0.020 | $0.100 |
| Output | $0.100 | $0.500 |
| Cache read | $0.0020 | $0.010 |
| Cache write (1 hour) | $0.040 | $0.200 |
Cache writes are billed at the 1-hour tier (2 × input).
Requests over 100K tokens: input × 5, output × 5.
Minimum $0.0005 per request; failed requests are free.
Specs
- Context
- 1M
- Max output
- 128K
- Capabilities
- TextTool useReasoning
- Endpoints
- POST /v1/messages · AnthropicPOST /v1/chat/completions · OpenAI-compatible
Cost examples
- A chat turn (2,000 in / 500 out)≈ $0.00009
- A coding turn (60,000 in / 4,000 out)≈ $0.0016
- Long-document Q&A (200,000 in / 2,000 out)≈ $0.0042
Examples
curl https://tokenarmy.shop/v1/messages \ -H "x-api-key: $TOKENARMY_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "claude-haiku-5-5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}] }'