Claude Haiku 5.5
Anthropicclaude-haikuActive
For high-volume, latency-sensitive tasks such as classification, extraction and routing.
- Released
- 2026-10-07
- Knowledge cutoff
- 2026-06
- Context window
- 1,000,000 tokens
- Max input
- —
- Max output
- 128,000 tokens
- Modalities
- text, image → text
- Reasoning
- Yes
- Tool calling
- Yes
Prices by provider
Exact USD list prices. — means the price is unknown (not free). History is append-only: a change adds a new entry.
Amazon Bedrock · Global cross-Region inference
Model id: global.anthropic.claude-haiku-5-5
| Meter | Standard | Unit |
|---|---|---|
| Input | $0.10 | per 1M tokens |
| Output | $0.50 | per 1M tokens |
| Cache read | $0.01 | per 1M tokens |
| Cache write (5m) | $0.125 | per 1M tokens |
| Cache write (1h) | $0.20 | per 1M tokens |
| Prompts over 100,000 tokens (whole request) | ||
| Input | $0.50 | per 1M tokens |
| Output | $2.50 | per 1M tokens |
| Cache read | $0.05 | per 1M tokens |
| Cache write (5m) | $0.625 | per 1M tokens |
| Cache write (1h) | $1.00 | per 1M tokens |
Prices for global.anthropic.claude-haiku-5-5 on Amazon Bedrock
- Effective from
- 2026-10-09
- Source
- Provider price list, fetched 2026-10-09 19:52:00 UTC, version
20261008235637 - Source entry
Claude Haiku 5.5 / On-demand Inference / *_global_standard and *_long_ctx_global_standard- Verify at
- https://aws.amazon.com/bedrock/pricing/
- Notes
- AWS price list for us-east-1, global usage types. The long_ctx usage types apply above 100,000 prompt tokens (threshold from Anthropic's long context pricing).
No earlier prices recorded.
API example
aws bedrock-runtime converse \
--region us-east-1 \
--model-id global.anthropic.claude-haiku-5-5 \
--messages '[{"role": "user", "content": [{"text": "Hello"}]}]'Amazon Bedrock · US cross-Region inference
Model id: us.anthropic.claude-haiku-5-5
| Meter | Standard | Unit |
|---|---|---|
| Input | $0.11 | per 1M tokens |
| Output | $0.55 | per 1M tokens |
| Cache read | $0.011 | per 1M tokens |
| Cache write (5m) | $0.1375 | per 1M tokens |
| Cache write (1h) | $0.22 | per 1M tokens |
| Prompts over 100,000 tokens (whole request) | ||
| Input | $0.55 | per 1M tokens |
| Output | $2.75 | per 1M tokens |
| Cache read | $0.055 | per 1M tokens |
| Cache write (5m) | $0.6875 | per 1M tokens |
| Cache write (1h) | $1.10 | per 1M tokens |
Prices for us.anthropic.claude-haiku-5-5 on Amazon Bedrock
- Effective from
- 2026-10-09
- Source
- Provider price list, fetched 2026-10-09 19:52:00 UTC, version
20261008235637 - Source entry
Claude Haiku 5.5 / On-demand Inference / *_standard and *_long_ctx_standard- Verify at
- https://aws.amazon.com/bedrock/pricing/
- Notes
- AWS price list for us-east-1, regional usage types (10% above global). The long_ctx usage types apply above 100,000 prompt tokens.
No earlier prices recorded.
API example
aws bedrock-runtime converse \
--region us-east-1 \
--model-id us.anthropic.claude-haiku-5-5 \
--messages '[{"role": "user", "content": [{"text": "Hello"}]}]'Anthropic
Model id: claude-haiku-5-5
| Meter | Standard | Batch | Unit |
|---|---|---|---|
| Input | $0.10 | $0.05 | per 1M tokens |
| Output | $0.50 | $0.25 | per 1M tokens |
| Cache read | $0.01 | — | per 1M tokens |
| Cache write (5m) | $0.125 | — | per 1M tokens |
| Cache write (1h) | $0.20 | — | per 1M tokens |
| Search | $0.01 | — | per search |
| Prompts over 100,000 tokens (whole request) | |||
| Input | $0.50 | $0.25 | per 1M tokens |
| Output | $2.50 | $1.25 | per 1M tokens |
| Cache read | $0.05 | — | per 1M tokens |
| Cache write (5m) | $0.625 | — | per 1M tokens |
| Cache write (1h) | $1.00 | — | per 1M tokens |
Prices for claude-haiku-5-5 on Anthropic
- Effective from
- 2026-10-09
- Source
- Provider pricing page, fetched 2026-10-09 19:33:00 UTC
- Notes
- Priced by prompt length: a request whose prompt (all input tokens, cache reads and writes included) is over 100,000 tokens pays the higher rates. Web search is $10 per 1,000 searches.
No earlier prices recorded.
API example
curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_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"}]}'OpenRouter
Model id: anthropic/claude-haiku-5.5
| Meter | Standard | Batch | Unit |
|---|---|---|---|
| Input | $0.10 | $0.05 | per 1M tokens |
| Output | $0.50 | $0.25 | per 1M tokens |
| Cache read | $0.01 | $0.005 | per 1M tokens |
| Cache write (5m) | $0.125 | $0.0625 | per 1M tokens |
| Cache write (1h) | $0.20 | $0.10 | per 1M tokens |
| Search | $0.01 | $0.01 | per search |
| Prompts over 100,000 tokens (whole request) | |||
| Input | $0.50 | $0.25 | per 1M tokens |
| Output | $2.50 | $1.25 | per 1M tokens |
| Cache read | $0.05 | $0.025 | per 1M tokens |
| Cache write (5m) | $0.625 | $0.3125 | per 1M tokens |
| Cache write (1h) | $1.00 | $0.50 | per 1M tokens |
Prices for anthropic/claude-haiku-5.5 on OpenRouter
- Effective from
- 2026-10-09
- Source
- OpenRouter API, fetched 2026-10-09 19:37:00 UTC
- Source entry
anthropic/claude-haiku-5.5- Notes
- Tiers are OpenRouter pricing.overrides with min_prompt_tokens = 100000. Batch rates are the separate anthropic/claude-haiku-5.5:batch id.
No earlier prices recorded.
API example
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "anthropic/claude-haiku-5.5", "messages": [{"role": "user", "content": "Hello"}]}'Model ids
| Provider | Id to send | Also accepted |
|---|---|---|
| Amazon Bedrock Global cross-Region inference | global.anthropic.claude-haiku-5-5 | |
| Amazon Bedrock US cross-Region inference | us.anthropic.claude-haiku-5-5 | |
| Anthropic | claude-haiku-5-5 | |
| OpenRouter | anthropic/claude-haiku-5.5 | |
This model as JSON
curl -s https://models.omg.bitop.dev/api/v1/models/claude-haiku-5-5.json