Anthropic · Released Feb 4, 2026
Claude Opus 4.6
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...
- #1METR time horizon
- #1DeepResearch Bench
- Top 10%SWE-bench Verified
- #1Cybench
- Released
- Feb 4 2026
- Context window
- 1M 128K out
- Input / 1M tokens
- $5.00 from $4.29
- Output / 1M tokens
- $25.00 from $21.46
Where to run it
44 providers compared
Included in GitLab Duo. Cheapest: Poe at $4.29 / $21.46 per 1M input / output tokens — 22% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| GitLab Duosubscription plan | Plan | Plan | Plan | 1M | 128K | — | Plan |
| Poe | $4.29 | $21.46 | $0.43 | 983K | 128K | — | Cheapest |
| Claude Platform on AWS | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Azureglobal | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Googleglobal | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Anthropic | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Amazon Bedrock | $5.00 | $25.00 | $0.50 | 1M | 128K | 99.9%24h | +16% |
| NanoGPT | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| FrogBot | $5.00 | $25.00 | $0.50 | 200K | 128K | — | +16% |
| Cloudflare AI Gateway | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| GMI Cloud | $5.00 | $25.00 | $0.50 | 410K | 128K | — | +16% |
| Venice AI | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Snowflake Cortex | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Kilo Gateway | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Vercel AI Gateway | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| LLM Gateway | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| FreeModel | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Databricks | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Pioneer | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| SAP AI Core | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| AIHubMix | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| DigitalOcean | $5.00 | $25.00 | $0.50 | 200K | 8K | — | +16% |
| ZenMux | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Auriko | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Perplexity Agent | $5.00 | $25.00 | $0.50 | 200K | 128K | — | +16% |
| Vertex | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Jiekou.AI | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Prime Inference | $5.00 | $25.00 | — | 1M | 128K | — | +16% |
| Neon | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Azure Cognitive Services | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Abacus | $5.00 | $25.00 | — | 1M | 128K | — | +16% |
| Tempr Gateway | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| DevPass (LLM Gateway) | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Merge Gateway | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Ofox | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Impossibl | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| OrcaRouter | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| OpenCode | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| NEAR AI Cloud | $5.00 | $25.00 | $0.50 | 200K | 128K | — | +16% |
| Vertex (Anthropic) | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Eden AI | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Opper | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Cortecs | $5.31 | $26.56 | $0.53 | 1M | 128K | — | +24% |
| Googleeurope | $5.50 | $27.50 | $0.55 | 1M | 128K | 100%24h | +28% |
| Requesty | $5.50 | $27.50 | $0.55 | 1M | 128K | — | +28% |
Value
Price vs. performance
Claude Opus 4.6 Other Anthropic Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
25 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| FrontierCodeSoftware engineering · Mergeable fixes for hard open-source issues | 26.6% | #35of 41 | Claude Opus 5.554.6% |
| SWE-bench VerifiedSoftware engineering · Real GitHub issues fixed in Python repos | 78.7% | #3of 32 | Claude Opus 4.783.5% |
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 79.8% | #5of 40 | GPT-5.584.7% |
| GBAEvalSoftware engineering · Build a Game Boy Advance emulator from scratch | 44.1% | #11of 23 | Claude Opus 579.6% |
| GSOSoftware engineering · Optimize real code to make it significantly faster | 41.2% | #7of 27 | Claude Fable 5.188.2% |
| METR time horizonSoftware engineering · Length of software task solved more often than not | 12 h | #1of 23 | This model |
| APEX-AgentsAgents & computer use · Long professional tasks in banking, consulting and law | 46.3% | #33of 51 | Gemini 4 Argon82.4% |
| Remote Labor IndexAgents & computer use · Real paid freelance projects done end-to-end | 4.2% | #9of 13 | Claude Opus 5.521.3% |
| Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) | $8,018 | #13of 61 | GPT-6 Astra$15,515 |
| DeepResearch BenchWriting & content · Find and synthesize information from the web | 55.3% | #1of 21 | This model |
| SimpleQA VerifiedWriting & content · Factual accuracy on 1,000 short questions | 47.0% | #32of 79 | Gemini 4 Argon76.0% |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1556 | #33of 90 | Claude Opus 5.51820 |
| Furniture AssemblyDesign & visual · Spot mistakes in photos of IKEA builds | 28.3% | #25of 34 | Claude Opus 5.583.3% |
| CybenchCybersecurity · Find and exploit vulnerabilities in sandboxed challenges | 93.0% | #1of 10 | This model |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 90.5% | #37of 122 | Gemini 4 Argon96.4% |
| Humanity's Last ExamReasoning & knowledge · Expert questions across 100+ subjects | 34.4% | #9of 32 | GPT-6 Astra54.8% |
| ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles | 69.2% | #23of 75 | GPT-6 Astra95.0% |
| ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples | 94.0% | #20of 75 | Gemini 4 Argon98.5% |
| SimpleBenchReasoning & knowledge · Common-sense trick questions about space, time and people | 67.6% | #13of 58 | Claude Fable 581.9% |
| Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles | 21.0% | #58of 83 | GPT-6 Astra76.0% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 55.8% | #12of 123 | Claude Sonnet 5.568.3% |
| FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) | 66.0% | #31of 87 | GPT-6.1 Sol93.7% |
| FrontierMath Tier 4Maths · Exceptionally hard research-level problems | 26.8% | #34of 64 | GPT-6.1 Sol100.0% |
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 50.0% | #31of 70 | Claude Sonnet 5.5100.0% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 94.4% | #39of 120 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
anthropic/claude-opus-4.6- Developer
- Anthropic
- Release date
- Feb 4, 2026 ·
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- API price
- $5.00 / $25.00 per 1M input / output tokens
- Providers
- 44
- Input types
- text, image, file
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.