← Model list
Claude Sonnet 4.6
anthropic·anthropic/claude-sonnet-4-6·GA·Closed·claude-sonnet series
Claude workhorse for coding agents, careful analysis, and production cost control
At a glance
Official price$3.00 / $15.00 per 1M
Cache read $0.30 · Anthropic
Lowest paid$0.90 / $5.55
Xpersona Gateway · 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 cutoff2025-08-31
Released / updated2026-02-17 / 2026-03-13
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Adaptive Reasoning, Max Effort
Intelligence48.4
Value23
Coding63
Agentic42.1
Output speed55 tok/s
TTFT149.24 s
Cost per task$1.2182
Value formulaIQ 48.4 ÷ min blended $2.063 = 23
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoning, Low EffortIQ 35.1 · 44 tok/s
Non-reasoning, High EffortIQ 36.8 · 43 tok/s
Adaptive Reasoning, Max EffortIQ 48.4 · 55 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 44 providers42 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Xpersona | Gateway | $0.90 | $5.55 | $0.09 | — | 200,000 ⚠ | 128,000 | |
| Poe anthropic/claude-sonnet-4.6 | Gateway | $2.60 | $13.00 | $0.26 | $3.20 | 983,040 ⚠ | 128,000 | |
| Requesty | Gateway | $2.70 | $13.50 | $0.27 | $3.38 | 1,000,000 | 128,000 | |
| OrcaRouter anthropic/claude-sonnet-4.6 | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 64,000 | |
| NanoGPT anthropic/claude-sonnet-4.6 | Gateway | $3.00 | $15.00 | $0.30 | — | 1,000,000 | 128,000 | |
| Vertex claude-sonnet-4-6@default | First-party | $3.00 tiered >200K: $6.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 128,000 | |
| Impossibl | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 64,000 | |
| OpenRouter anthropic/claude-sonnet-4.6 | Gateway | $3.00 tiered >200K: $6.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 128,000 | |
| Vertex (Anthropic) claude-sonnet-4-6@default | Cloud | $3.00 tiered >200K: $6.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 128,000 | |
| Auriko | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 64,000 | |
| AnthropicOfficial | First-party | $3.00 | $15.00 | $0.30 | $3.75 | 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
1Xpersona$360.30
2Poe$889.20
3Requesty$923.40
4OrcaRouter$1,026.00
5NanoGPT$1,026.00
6Vertex$1,026.00
13Anthropic · Official$1,026.00
Switch to Xpersona to save $665.70/mo (65%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark11 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Atlas Codebase QnA | harness: Claude Code | 31.2 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Claude Code | 32.21 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Claude Code | 31.76 | score | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Claude Code · variant: medium | 49.4 | average pass@1 | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Claude Code · variant: medium | 70.3 | pass@1 | Source ↗ |
| SWE-Bench Pro | harness: Claude Code · variant: medium · dataset: hard-aa | 14.9 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Claude Code · variant: medium · v2.1 | 63.1 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Terminus-2 · v2.1 | 67 | success rate | Source ↗ |
| Humanity's Last Exam | variant: no tools | 34.6 | accuracy | Source ↗ |
| Humanity's Last Exam | variant: with tools | 46.8 | accuracy | Source ↗ |
| OSWorld-Verified | — | 78.5 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = nonebudget_tokens ≥ 1,024 ≤ 63,999Toggle (on / off)
3 / 44 providers expose no reasoning control (reasoning_options: []).
Related models
Claude Sonnet 5same series$2.00 / $10.00Claude Sonnet 5 Thinkingsame series$2.00 / $10.00Claude Sonnet 5 (JP)same series$2.00 / $10.00GLM-5.2cheaper alternative$1.40 / $4.40DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended