Claude Opus 4.6
Anthropic · Proprietary · Released Feb 4, 2026 · anthropic/claude-opus-4.6
1M contextVisionToolsReasoningStructured outputPrompt caching
Available from 6 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 Azure | $5.00 | $25.00 | $0.50 | 1M | — | 1.9s | 47 tok/s | 5/5 | 97.7% |
 Google | $5.00 | $25.00 | $0.50 | 1M | — | 1.2s | 63 tok/s | 5/5 | 100.0% |
 Amazon Bedrock | $5.00 | $25.00 | $0.50 | 1M | — | 1.9s | 89 tok/s | 5/5 | 99.8% |
 Anthropic1ST PARTY | $5.00 | $25.00 | $0.50 | 1M | — | 1.8s | 39 tok/s | 5/5 | 99.5% |
| CPOClaude Platform on AWS | $5.00 | $25.00 | $0.50 | 1M | — | 1.4s | 40 tok/s | 5/5 | 96.5% |
| Google | $5.50 | $27.50 | $0.55 | 1M | — | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 44 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$5.00 / $25.00
per MTok in / out
BATCH
$2.50 / $12.50
async batch
CACHE READ $0.50CACHE WRITE $6.25WEB SEARCH $0.01 / searchCACHE WRITE 1H $10.00 / MTok
About
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Specifications
Context window1,000,000
Max output128,000
Modalities intext, image, file
Modalities outtext
LicenseProprietary
ReleasedFeb 4, 2026
TokenizerClaude
Related
Embed badge
[](https://modelindex.ai/models/anthropic/claude-opus-4.6)Sources
OpenRouter API4 minutes ago
AGGREGATORModelIndex benchmarks44 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.