Claude Opus 5.5 vs DeepSeek V4 Pro 0813
API pricing, context, and independently measured performance, side by side. DeepSeek V4 Pro 0813 starts 90% cheaper on input than Claude Opus 5.5 at list prices.
Claude Opus 5.5
Anthropic · released Sep 22, 2026
Best input$4.00 / MTok
Best output$20.00 / MTok
Context1M
Providers13
Fastest measured3.7s° TTFT · 216 tok/s
VisionToolsReasoningStructured outputPrompt caching
DeepSeek V4 Pro 0813
DeepSeek · released Aug 12, 2026
Best input$0.40 / MTok
Best output$1.20 / MTok
Context1.05M
Providers26
Fastest measured0.59s° TTFT · 102 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Claude Opus 5.5 |  Amazon Bedrock | $4.00 | $20.00 | — | — | — |
| Claude Opus 5.5 |  Azure | $4.00 | $20.00 | 3.7s° | 216° tok/s | — |
| Claude Opus 5.5 |  Google | $4.00 | $20.00 | 3.9s° | 164° tok/s | — |
| DeepSeek V4 Pro 0813 |  Baidu | $0.40 | $1.20 | 0.81s° | 55° tok/s | — |
| DeepSeek V4 Pro 0813 | SRSail Research | $0.40 | $4.30 | 2.6s° | 28° tok/s | — |
| DeepSeek V4 Pro 0813 |  StreamLake | $0.462 | $1.39 | 2.3s° | 100° tok/s | 5/5 |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page