← Model list
Claude Opus 4.6
anthropic·anthropic/claude-opus-4-6·GA·Closed·claude-opus series
High-end Claude for difficult coding, planning, and slower expert reasoning
At a glance
Official price$5.00 / $25.00 per 1M
Cache read $0.50 · Anthropic
Lowest paid$4.30 / $21.00
Poe Gateway · 1.4× spread
Context1,000,000
⚠ Providers report 200,000–1,000,000; the table below is authoritative
Output limit128,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF
Knowledge cutoff2025-05-31
Released / updated2026-02-05 / 2026-03-13
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Adaptive Reasoning, Max Effort
Intelligence44.9
Value5
Coding—
Agentic—
Output speed39 tok/s
TTFT15.46 s
Value formulaIQ 44.9 ÷ min blended $8.475 = 5
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoning, High EffortIQ 38.8 · 36 tok/s
Adaptive Reasoning, Max EffortIQ 44.9 · 39 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 38 providers36 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Poe anthropic/claude-opus-4.6 | Gateway | $4.30 | $21.00 | $0.43 | $5.30 | 983,040 ⚠ | 128,000 | |
| Requesty | Gateway | $4.50 | $22.50 | $0.45 | $5.63 | 1,000,000 | 128,000 | |
| OrcaRouter anthropic/claude-opus-4.6 | Gateway | $5.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| Vertex claude-opus-4-6@default | First-party | $5.00 tiered >200K: $10.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| Impossibl | Gateway | $5.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| Jiekou.AI | Gateway | $5.00 | $25.00 | — | — | 1,000,000 | 128,000 | |
| OpenRouter anthropic/claude-opus-4.6 | Gateway | $5.00 tiered >200K: $10.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| Vertex (Anthropic) claude-opus-4-6@default | Cloud | $5.00 tiered >200K: $10.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| Auriko | Gateway | $5.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| AnthropicOfficial | First-party | $5.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Poe$1,445.60
2Requesty$1,539.00
3OrcaRouter$1,710.00
4Vertex$1,710.00
5Impossibl$1,710.00
6OpenRouter$1,710.00
9Anthropic · Official$1,710.00
Switch to Poe to save $264.40/mo (15%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark10 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | dataset: public | 51.9 | resolve rate | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Claude Code | 33.3 | score | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Mini-SWE-Agent | 30 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Claude Code | 35.58 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Claude Code | 36.67 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Mini-SWE-Agent | 36.08 | score | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Claude Code · variant: medium | 51.3 | average pass@1 | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Claude Code · variant: medium | 71.9 | pass@1 | Source ↗ |
| SWE-Bench Pro | harness: Claude Code · variant: medium · dataset: hard-aa | 11.8 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Claude Code · variant: medium · v2.1 | 70.2 | pass@1 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokens ≥ 1,024 ≤ 127,999Toggle (on / off)effort = xhigh
2 / 38 providers expose no reasoning control (reasoning_options: []).
Experimental modes5 items
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | OrcaRouter | $30.00 | $150 | $3.00 | $37.50 |
| fast | Databricks | $30.00 | $150 | $3.00 | $37.50 |
| fast | Merge Gateway | $30.00 | $150 | $3.00 | $37.50 |
| fast | GitHub Copilot | $30.00 | $150 | $3.00 | $37.50 |
| fast | AnyAPI | $30.00 | $150 | $3.00 | $37.50 |
Related models
Claude Opus 5same series$5.00 / $25.00Claude Opus 5 (Fast)same series$12.00 / $60.00Claude Opus 5 (EU)same series$5.50 / $27.50GLM-5.2cheaper alternative$1.40 / $4.40DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GPT-5.4cheaper alternative$2.50 / $15.00
Price historyone sample accumulated per data sync
Input listOutput listMin blended