anthropic
Anthropic: Claude Opus 4.6 (batch)
anthropic/claude-opus-4.6:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Anthropic/claude-opus-4.6:batch is the batch variant of Anthropic's Claude Opus 4.6, listed in the OpenRouter catalog under canonical ID anthropic/claude-4.6-opus-20260205. It accepts text, image, and file inputs and produces text output, with a catalog-stated context window of one million tokens. The catalog description positions it for coding and long-running agentic professional work. Optional reasoning is supported at several effort levels but is disabled by default. An independent model card was not available in this source pack, so all details come from OpenRouter's catalog.[1]
Strengths
- Accepts text, image, and file inputs and supports tool use, structured outputs, and response formatting, per the OpenRouter catalog's listed parameters.[1]
- Catalog-stated context window of one million tokens, which would suit very large inputs.[1]
- Reasoning is optional with multiple effort levels from none to max; it is off by default and uses high effort when enabled without an explicit setting.[1]
Limitations
- Evidence is catalog-only; no independent model card was available in this source pack, so capabilities are provider-reported rather than independently verified.[1]
- Output is text only; the listed modalities show no image or file generation.[1]
- Knowledge cutoff is not listed and independent evaluation data is absent; validate against real workloads before relying on it.[1]
Where to use it
- Editorial suggestion: batch processing of large document collections, given file input support and the catalog's long-context claim; worth validating on representative workloads.[1]
- The catalog positions it for coding and multi-step agentic workflows; teams could evaluate it for those tasks rather than assume proven results.[1]
- Non-latency-critical jobs may fit the batch variant identified in the listing; confirm actual batch behavior and limits before adoption.[1]
Sources
- [1] OpenRouter catalog · Anthropic: Claude Opus 4.6 (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Specifications
- Model ID
- anthropic/claude-opus-4.6:batch
- Canonical ID
- anthropic/claude-4.6-opus-20260205
- Creator
- anthropic
- Added to OpenRouter
- 04.02.2026
- 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 $2.5 / out $12.5
- 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 | No measurement | reasoning: optional · default high · efforts: max, 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 high · efforts: max, 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 |
|---|---|---|---|---|
| Design Arena | agents · agenticgamedevwin rate 45.5% · rank 11 | 1,146Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 61% · rank 18 | 1,180Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · blender3dwin rate 37.2% · rank 20 | 1,008Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · codetovideowin rate 42.9% · rank 16 | 1,110Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 59.2% · rank 15 | 1,199Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 57.3% · rank 20 | 1,202Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · pdfwin rate 54.2% · rank 16 | 1,198Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · spreadsheetwin rate 60.5% · rank 10 | 1,221Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 55.6% · rank 25 | 1,187Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 62.5% · rank 28 | 1,257Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 61.9% · rank 16 | 1,250Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 61.2% · rank 24 | 1,279Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 58.7% · rank 21 | 1,277Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 61% · rank 25 | 1,268Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 60.9% · rank 24 | 1,219Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 59.8% · rank 29 | 1,276Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 61.1% · rank 22 | 1,284Elo | AA — next 20% 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) |
|---|---|---|---|---|---|---|
| Anthropic | 1,000,000 | $2.5 | $12.5 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.