anthropic
Anthropic: Claude Haiku 4.5
anthropic/claude-haiku-4.5
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, Claude Haiku 4.5 (anthropic/claude-haiku-4.5) is presented by Anthropic as its fastest and most efficient model, aimed at near-frontier quality at lower cost and latency than larger Claude models. The listing records text output from text, image, and file inputs, a 200,000-token context window, tool calling, structured outputs, and optional reasoning controls. Benchmark, arena, and pricing figures appear in the structured catalog data. Because the only evidence is this catalog entry and no independent model card was included, treat the vendor-facing description as unverified and validate it on your own workload.[1]
Strengths
- Positioned by Anthropic, per the OpenRouter catalog, as a fast, cost- and latency-efficient option relative to larger Claude models; this is a catalog-reported claim, not an independently measured result.[1]
- Accepts text, image, and file inputs with text output and a 200,000-token context window, per the catalog listing.[1]
- Exposes tool calling, structured outputs, response formatting, and optional reasoning parameters, which suits integration scenarios according to the listed supported parameters.[1]
Limitations
- Evidence is catalog-only: OpenRouter's entry was the sole source in this pack, no independent model card was available, and the vendor-facing positioning should be validated on real workloads before adoption.[1]
- Measured results are less flattering than the description: the design-arena entries recorded in the catalog show losing records (win rates below parity) in every listed category, pointing to unremarkable measured design performance.[1]
- The catalog does not state a knowledge cutoff, so that property is simply unknown rather than absent.[1]
Where to use it
- High-volume text tasks where latency and unit cost matter, such as chat, summarization, or classification; suggested based on the catalog's efficiency positioning, not proven results.[1]
- Document- or image-aware pipelines that need text answers, using the listed image and file input support; worth piloting to confirm accuracy on your data.[1]
- Agent or API integrations requiring tool calls or schema-constrained output, given the listed tools and structured_outputs parameters.[1]
Sources
- [1] OpenRouter catalog · Anthropic: Claude Haiku 4.5Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Specifications
- Model ID
- anthropic/claude-haiku-4.5
- Canonical ID
- anthropic/claude-4.5-haiku-20251001
- Creator
- anthropic
- Added to OpenRouter
- 15.10.2025
- Context length
- 200,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1 / out $5
- 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 | CC — below the B band | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | BB — next 30% of the cohort | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| 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 | 7.4 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 43.9 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 8 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 41.1% · rank 110 | 1,055Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · asciiartwin rate 49.3% · rank 52 | 1,135Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 44.9% · rank 105 | 1,105Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 45.7% · rank 97 | 1,122Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 44.7% · rank 101 | 1,088Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 39.1% · rank 88 | 1,017Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 42.6% · rank 103 | 1,091Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 45.1% · rank 106 | 1,115Elo | CC — below the B band | 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) |
|---|---|---|---|---|---|---|
| Azure | 200,000 | $1 | $5 | — | — | 100% |
| Amazon Bedrock | 200,000 | $1 | $5 | — | — | 100% |
| 200,000 | $1 | $5 | — | — | 100% | |
| Anthropic | 200,000 | $1 | $5 | — | — | 100% |
| Amazon Bedrock | 200,000 | $1.1 | $5.5 | — | — | 100% |
| 200,000 | $1.1 | $5.5 | — | — | — | |
| Amazon Bedrock | 200,000 | $1.1 | $5.5 | — | — | 100% |
| 200,000 | $1.1 | $5.5 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.