anthropic
Anthropic: Claude Haiku 5.5
anthropic/claude-haiku-5.5
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to the OpenRouter catalog, anthropic/claude-haiku-5.5 is Anthropic's small, fast model aimed at high-volume, cost-sensitive work such as summarization, subagents, and browser use, presented as the successor to Claude Haiku 4.5 with stronger coding and computer use. It accepts text, image, and file inputs and returns text within a one-million-token context window. Optional reasoning is supported at several effort levels, alongside tool calling and structured outputs. An independent model card was not available in this source pack.[1]
Strengths
- The OpenRouter catalog lists multimodal input support for text, images, and files, with a one-million-token context window.[1]
- Optional reasoning with multiple effort levels is supported, along with tool calling, structured outputs, and response format parameters.[1]
- The catalog describes it as a small, fast model positioned for high-volume, cost-sensitive workloads.[1]
Limitations
- All evidence comes from the OpenRouter catalog only; no independent model card or first-party documentation was available in this source pack.[1]
- The catalog does not specify a knowledge cutoff or safety evaluations; reported capabilities should be validated on your own workloads.[1]
- The catalog's benchmark and index listings are measured results that may not transfer to specific tasks.[1]
Where to use it
- The catalog suggests high-volume summarization and text processing pipelines; confirm output quality on representative data.[1]
- Subagent and browser-use automation are listed as intended applications; test integration with your tooling.[1]
- A plausible fit for cost-sensitive applications needing image or file input, per the catalog description.[1]
Sources
- [1] OpenRouter catalog · Anthropic: Claude Haiku 5.5Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Specifications
- Model ID
- anthropic/claude-haiku-5.5
- Canonical ID
- anthropic/claude-haiku-5.5-20261007
- Creator
- anthropic
- Added to OpenRouter
- 07.10.2026
- Context length
- 1,000,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.100 / out $0.500
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | AA — next 20% of the cohort | reasoning: optional · default medium · efforts: max, xhigh, high, medium, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default medium · efforts: max, xhigh, high, medium, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 36.5 | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 55.8% · rank 14 | 1,327Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 50.9% · rank 22 | 1,216Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 50.3% · rank 25 | 1,278Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 50.4% · rank 19 | 1,279Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 52.5% · rank 14 | 1,316Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 43.4% · rank 31 | 1,194Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 50.8% · rank 30 | 1,274Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 48.2% · rank 41 | 1,254Elo | BB — next 30% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| 1,000,000 | $0.100 | $0.500 | — | — | 100% | |
| Claude Platform on AWS | 1,000,000 | $0.100 | $0.500 | — | — | 100% |
| Azure | 1,000,000 | $0.100 | $0.500 | — | — | 83.33% |
| Anthropic | 1,000,000 | $0.100 | $0.500 | — | — | 73.33% |
| Amazon Bedrock | 1,000,000 | $0.100 | $0.500 | — | — | 100% |
| 1,000,000 | $0.110 | $0.550 | — | — | 100% | |
| 1,000,000 | $0.110 | $0.550 | — | — | 100% | |
| Azure | 1,000,000 | $0.110 | $0.550 | — | — | — |
| Amazon Bedrock | 1,000,000 | $0.110 | $0.550 | — | — | 100% |
| Amazon Bedrock | 1,000,000 | $0.110 | $0.550 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
- Four Amazon Bedrock request settings that change inference costsAn AWS walkthrough shows how cache duration, service tier, reasoning effort, and maxTokens change token counts and rates on Amazon Bedrock, with tests on Claude and Nova models.
- LLM batch APIs cut prices in half, but only for traffic that can waitA cost-modeling blog explains how batch discounts apply only to deferrable calls, why batch and caching stack multiplicatively, the billing bug this caused, and why dropping a model tier usually saves more.
- Google DeepMind and Artificial Analysis Introduce MKA, a Benchmark for Visually Grounded Agent WorkMKA is a 200-task benchmark that measures whether AI agents can extract decisive evidence from blueprints, scans, and charts and turn it into professional deliverables.