Claude Sonnet 5
✓ VERIFIED BY ANTHROPICAnthropic · Proprietary · Released Jun 30, 2026 · anthropic/claude-sonnet-5
Best $2.00 in / $10.00 out via Anthropic
1M contextVisionToolsReasoningStructured outputPrompt caching
Available from 12 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 9 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $1.30 | $6.50 | — | — | — | 3.2s | 93 tok/s | — | |
| $1.50 | $7.50 | — | — | — | 2.7s | 81 tok/s | — | |
| $2.00 | $10.00 | $0.20 | 1M | — | 1.4s | 133 tok/s | 100.0% | |
| $2.00 | $10.00 | $0.20 | 1M | — | 1.8s° | 112° tok/s | 100.0% | |
| $2.00 | $10.00 | $0.20 | 1M | — | 1.7s° | 100° tok/s | 100.0% | |
| $2.00 | $10.00 | $0.20 | 1M | — | 1.1s° | 125° tok/s | 100.0% | |
| $2.00 | $10.00 | $0.20 | 1M | — | 1.7s° | 111° tok/s | 100.0% | |
| $2.20 | $11.00 | $0.22 | 1M | — | — | — | 100.0% | |
| $2.20 | $11.00 | $0.22 | 1M | — | — | — | 100.0% | |
| $2.20 | $11.00 | $0.22 | 1M | — | — | — | — | |
| $2.20 | $11.00 | $0.22 | 1M | — | — | — | 100.0% | |
| $2.20 | $11.00 | $0.22 | 1M | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured against the provider API directly; ° = routed via OpenRouter (adds a hop) · methodology v1.1 · measured 9 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Quality benchmarksCURATED AUG 24, 2026
Third-party reported results, hand-curated with sources — not measured by ModelIndex. Our own measured serving data (TTFT/TPS/SMOKE) is in the providers table above.
Pricing variants · USD / MTok in / out
STANDARD
$2.00 / $10.00
per MTok in / out
BATCH
$1.00 / $5.00
async batch
CACHE READ $0.20CACHE WRITE $2.50WEB SEARCH $0.01 / searchCACHE WRITE 1H $4.00 / MTok
Recent changesRSS ↗
Sep 23, 2026endpoint added · cheaperinference10 → 12
About
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Specifications
Context window1,000,000
Max output128,000
Modalities intext, image, file
Modalities outtext
LicenseProprietary
ReleasedJun 30, 2026
TokenizerClaude
Related
Embed badge
[](https://modelindex.ai/models/anthropic/claude-sonnet-5)Sources
anthropic ↗23 minutes ago
OFFICIAL PRICINGOpenRouter API23 minutes ago
AGGREGATORLiteLLM dataset23 minutes ago
AGGREGATORModelIndex benchmarks15 minutes ago
MEASURED✓ Verified against Anthropic’s own source.
Verified 23 minutes ago · list prices, not negotiated rates.