Anthropic · Released Apr 16, 2026
Claude Opus 4.7
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
- #1SWE-bench Verified
- Top 8%Terminal-Bench
- Top 10%Vending-Bench 2
- Top 18%LMCA
- Released
- Apr 16 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
50 providers compared
Included in GitLab Duo. Cheapest: Poe at $4.29 / $21.46 per 1M input / output tokens — 38% 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 | 1M | 128K | — | Cheapest |
| GMI Cloud | $4.50 | $22.50 | $0.45 | 410K | 128K | — | +5% |
| Claude Platform on AWS | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Googleglobal | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Amazon Bedrockglobal | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Anthropic | $5.00 | $25.00 | $0.50 | 1M | 128K | 100%24h | +16% |
| Azureglobal | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +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% |
| 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% |
| HPC-AI | $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% |
| Requesty | $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% |
| 302.AI | $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% |
| GitHub Copilot | $5.00 | $25.00 | $0.50 | 200K | 32K | — | +16% |
| Auriko | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Perplexity Agent | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Vertex | $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% |
| CrossModel | $5.00 | $25.00 | $0.50 | 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% |
| CommandCode | $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 | 1M | 128K | — | +16% |
| Vertex (Anthropic) | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Eden AI | $5.00 | $25.00 | $0.50 | 1M | 128K | — | +16% |
| Cortecs | $5.44 | $27.19 | $0.54 | 1M | 128K | — | +27% |
| Googleus | $5.50 | $27.50 | $0.55 | 1M | 128K | — | +28% |
| Amazon Bedrockeu-west-1 | $5.50 | $27.50 | $0.55 | 1M | 128K | — | +28% |
| Googleeurope | $5.50 | $27.50 | $0.55 | 1M | 128K | — | +28% |
| Opper | $5.50 | $27.50 | $0.55 | 1M | 64K | — | +28% |
| Kenari | $5.71 | $29.71 | $0.57 | 1M | 128K | — | +36% |
| AI/ML API | $6.88 | $34.38 | $0.69 | 1M | 128K | — | +60% |
Value
Price vs. performance
Claude Opus 4.7 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
29 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| FrontierCodeSoftware engineering · Mergeable fixes for hard open-source issues | 38.5% | #28of 41 | Claude Opus 5.554.6% |
| SWE-bench VerifiedSoftware engineering · Real GitHub issues fixed in Python repos | 83.5% | #1of 32 | This model |
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 80.2% | #3of 40 | GPT-5.584.7% |
| MirrorCodeSoftware engineering · Reimplement whole programs end-to-end without the source | 31.1% | #6of 10 | Claude Opus 5.577.4% |
| GBAEvalSoftware engineering · Build a Game Boy Advance emulator from scratch | 43.8% | #12of 23 | Claude Opus 579.6% |
| GSOSoftware engineering · Optimize real code to make it significantly faster | 44.1% | #6of 27 | Claude Fable 5.188.2% |
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 54.5% | #29of 102 | Claude Opus 5.566.9% |
| APEX-AgentsAgents & computer use · Long professional tasks in banking, consulting and law | 49.2% | #26of 51 | Gemini 4 Argon82.4% |
| OSWorld 2.0Agents & computer use · Long real-world desktop and web tasks | 18.2% | #4of 9 | Claude Opus 531.4% |
| Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) | $10,937 | #6of 61 | GPT-6 Astra$15,515 |
| PostTrainBenchAgents & computer use · Post-train small models under a fixed compute budget | 28.6% | #7of 11 | Claude Fable 541.8% |
| GDP.pdfWriting & content · Answer questions about real professional PDFs | 21.0% | #21of 38 | GPT-6.1 Sol35.0% |
| SimpleQA VerifiedWriting & content · Factual accuracy on 1,000 short questions | 51.7% | #24of 79 | Gemini 4 Argon76.0% |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1567 | #31of 90 | Claude Opus 5.51820 |
| Blueprint-Bench 2Design & visual · Turn apartment photos into 2D floor plans | 24.5% | #24of 32 | Gemini 4 Argon54.4% |
| Furniture AssemblyDesign & visual · Spot mistakes in photos of IKEA builds | 33.3% | #23of 34 | Claude Opus 5.583.3% |
| ExploitBenchCybersecurity · Exploit real, hardened security vulnerabilities | 26.5% | #2of 8 | GPT-5.547.4% |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 90.1% | #40of 122 | Gemini 4 Argon96.4% |
| Humanity's Last ExamReasoning & knowledge · Expert questions across 100+ subjects | 36.2% | #8of 32 | GPT-6 Astra54.8% |
| ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles | 75.8% | #17of 75 | GPT-6 Astra95.0% |
| ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples | 93.5% | #22of 75 | Gemini 4 Argon98.5% |
| SimpleBenchReasoning & knowledge · Common-sense trick questions about space, time and people | 61.7% | #16of 58 | Claude Fable 581.9% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 12.0% | #46of 111 | GPT-5.6 Sol32.3% |
| Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles | 41.0% | #35of 83 | GPT-6 Astra76.0% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 52.2% | #21of 123 | Claude Sonnet 5.568.3% |
| FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) | 70.2% | #27of 87 | GPT-6.1 Sol93.7% |
| FrontierMath Tier 4Maths · Exceptionally hard research-level problems | 31.7% | #28of 64 | GPT-6.1 Sol100.0% |
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 54.0% | #27of 70 | Claude Sonnet 5.5100.0% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 97.8% | #26of 120 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
anthropic/claude-opus-4.7- Developer
- Anthropic
- Release date
- Apr 16, 2026 ·
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- API price
- $5.00 / $25.00 per 1M input / output tokens
- Providers
- 50
- 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.