Anthropic
CurrentClaude Haiku 5.5
Anthropic's fastest, lowest-priced current model, from $0.10 input and $0.50 output per 1M tokens.
Anthropic describes it as
“For high-volume, latency-sensitive tasks such as classification, extraction, and routing”
Last verified:
Key facts
- Context window
- 1,000,000
- Max output
- 128,000
- Input price
- $0.10
- Output price
- $0.50
- Extended output (Batch API (beta))
- 300,000
- Released
- Oct 7, 2026
- Knowledge cutoff
- Jun 2026
- API model ID
- claude-haiku-5-5
tokens
tokens, default
$0.50 above 100K tokens
$2.50 above 100K tokens
tokens, special mode only
- Batch API (beta): Message Batches API only, with the output-300k-2026-03-24 beta header. Synchronous requests are limited to 128,000 output tokens.
- Anthropic's pages list a context window and a maximum output but do not state a separate maximum-input figure.
About Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's model for high-volume, latency-sensitive tasks such as classification, extraction and routing. It costs $0.10 input and $0.50 output per million tokens for prompts up to 100,000 tokens, and $0.50 and $2.50 above that. It has a 1,000,000-token context window and up to 128,000 output tokens.
API pricing
Per-token API prices from the provider's pricing page. Thresholds and processing modes are shown explicitly, not folded into one number.
| Rate | Prompts up to 100,000 tokens | Prompts over 100,000 tokens |
|---|---|---|
| Input | $0.10 | $0.50 |
| Cached input | $0.01 | $0.05 |
| Output | $0.50 | $2.50 |
| Cache write (5 minutes) | $0.125 | $0.625 |
| Cache write (1 hour) | $0.20 | $1.00 |
| Rate | Prompts up to 100,000 tokens | Prompts over 100,000 tokens |
|---|---|---|
| Input | $0.05 | $0.25 |
| Output | $0.25 | $1.25 |
- Cache write prices are shown for 5-minute and 1-hour retention.
- Setting inference_geo to "us" applies a 1.1x multiplier on Claude 4.6 and later models.
- A request whose prompt is over 100,000 tokens pays the higher prices. Prompt length counts all input tokens, including cache reads and cache writes, and each request is priced on its own.
- Unlike Anthropic's other current models, Haiku 5.5 does not include the full 1M context at one flat price.
Modalities and capabilities
What the provider documents for this model. “API tool” means it needs a provider tool or endpoint rather than being native to the model.
- Input modalities
- Text, Image, PDF
- Output modalities
- Text
- ReasoningReasoning: ✓ Yes
Adaptive thinking with an adjustable effort setting.
- Tool / function callingTool / function calling: ✓ Yes
- Structured outputsStructured outputs: ✓ Yes
- Web searchWeb search: ✓ Yes · API tool
Web search tool.
- Code executionCode execution: ✓ Yes · API tool
Code execution tool.
- Computer useComputer use: ✓ Yes · API tool
On the Claude API, through computer_toolset_20260801.
- Image generationImage generation: ✕ No
Output is text only.
- Prompt cachingPrompt caching: ✓ Yes
Minimum cacheable prompt length is 512 tokens.
- Batch APIBatch API: ✓ Yes
Benchmarks
Individual named benchmarks only: there is no overall score. Vendor-reported results come from the model maker's own launch materials. Scores from different sources, versions or settings are not directly comparable.
| Benchmark | Score | Source type | Reported by |
|---|---|---|---|
| AA-Briefcase (v1.1) | 1578 | Vendor-reported | AnthropicOct 7, 2026 |
| FrontierCode (v1.1, Main) | 46.4% | Vendor-reported | AnthropicOct 7, 2026 |
| GDPval-AA (v2.1) | 1620 | Vendor-reported | AnthropicOct 7, 2026 |
| Humanity's Last Exam (no tools) | 45.9% | Vendor-reported | AnthropicOct 7, 2026 |
| Humanity's Last Exam (with tools) | 57.4% | Vendor-reported | AnthropicOct 7, 2026 |
| OSWorld (v2.1, offline subset) | 72.4% | Vendor-reported | AnthropicOct 7, 2026 |
| Terminal-Bench (v4.0) | 39.2% | Vendor-reported | AnthropicOct 7, 2026 |
Availability and API identifiers
| Surface | Identifier |
|---|---|
| Claude APIEvery Claude model ID is a pinned snapshot; there is no separate dated ID. | claude-haiku-5-5 |
| Amazon Bedrock | anthropic.claude-haiku-5-5 |
| Google Cloud (Google-managed and Anthropic-managed) | claude-haiku-5-5 |
| Microsoft Foundry | claude-haiku-5-5 |
| Claude Platform on AWS | claude-haiku-5-5 |
Limitations and caveats
API vs. apps. These limits and prices describe the Claude API model. The Claude apps can apply different limits and are billed through subscriptions, not per token.
- Anthropic lists retirement as not sooner than October 7, 2027.
- Anthropic says Claude 4.7 and later models produce approximately 30% more tokens for the same text than earlier Claude models.
- Omit temperature, top_p and top_k, per Anthropic's page.
Sources
Last verified against these sources on Oct 31, 2026. Prices and limits change; follow the links for the live figure.
- Anthropic docs — Claude Haiku 5.5
Supports: status, release date, knowledge cutoff, context window, max output, modalities, pricing
OfficialChecked Oct 31, 2026
- Anthropic docs — Models overview
Supports: status, context window, max output, modalities, capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — Pricing
Supports: pricing
OfficialChecked Oct 31, 2026
- Anthropic docs — Structured outputs
Supports: capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — Web search tool
Supports: capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — Computer use tool
Supports: capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — Code execution tool
Supports: capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — PDF support
Supports: modalities, capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — Prompt caching
Supports: capabilities
OfficialChecked Oct 31, 2026
- Anthropic docs — Batch processing
Supports: capabilities
OfficialChecked Oct 31, 2026
- Anthropic — Claude Haiku 5.5 launch page
Supports: benchmarks
Anthropic launch page; scores are Anthropic-reported.
Vendor benchmarkChecked Oct 31, 2026