← Model list
Claude Sonnet 5
anthropic·anthropic/claude-sonnet-5·BETA·Closed·claude-sonnet series·NEW
Everyday Claude agent model for coding, planning, browsing, and general work
At a glance
Official price$2.00 / $10.00 per 1M
Cache read $0.20 · Anthropic
Lowest paid$1.44 / $7.20
UnoRouter Gateway · 2.1× spread
1 more $0 channels
Context1,000,000
Output limit128,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2026-01-31
Released / updated2026-06-30 / 2026-06-30
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Adaptive Reasoning, Max Effort
Intelligence55.3
Value19
Coding71.5
Agentic49.7
Output speed76 tok/s
TTFT184.48 s
Cost per task$1.7173
Value formulaIQ 55.3 ÷ min blended $2.880 = 19
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoning, High EffortIQ 42.6 · 58 tok/s
Adaptive Reasoning, Max EffortIQ 55.3 · 76 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 32 providers29 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari | Gateway | Free | — | — | 1,000,000 | 128,000 | ||
| UnoRouter | Gateway | $1.44 | $7.20 | — | — | 1,000,000 | 128,000 | |
| Requesty | Gateway | $1.80 | $9.00 | $0.18 | $2.25 | 1,000,000 | 128,000 | |
| NanoGPT | Gateway | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 | |
| Vertex claude-sonnet-5@default | First-party | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 | |
| Impossibl | Gateway | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 | |
| OpenRouter | Gateway | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 | |
| Vertex (Anthropic) claude-sonnet-5@default | Cloud | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 | |
| CrossModel | Gateway | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 | |
| AnthropicOfficial | First-party | $2.00 | $10.00 | $0.20 | $2.50 | 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
1Requesty$615.60
2UnoRouter$648.00
3NanoGPT$684.00
4Vertex$684.00
5Impossibl$684.00
6OpenRouter$684.00
9Anthropic · Official$684.00
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to Requesty to save $68.40/mo (10%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark7 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 85.2 | resolved | Source ↗ |
| SWE-Bench Pro | — | 63.2 | resolve rate | Source ↗ |
| SWE-Bench Multilingual | — | 78.3 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Terminus-2 · v2.1 | 80.4 | success rate | Source ↗ |
| OSWorld-Verified | — | 81.2 | success rate | Source ↗ |
| BrowseComp | variant: single agent | 84.7 | accuracy | Source ↗ |
| FrontierCode | vv1 | 38.8 | pass 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 ≥ 1,024Toggle (on / off)
4 / 32 providers expose no reasoning control (reasoning_options: []).
Related models
Claude Sonnet 5 Thinkingsame series$2.00 / $10.00Claude Sonnet 5 (JP)same series$2.00 / $10.00Claude Sonnet 5 (AU)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