DeepSeek V4 Pro 0423 vs Qwen3.8 27B
API pricing, context, and independently measured performance, side by side. Qwen3.8 27B starts 76% cheaper on input than DeepSeek V4 Pro 0423 at list prices.
DeepSeek V4 Pro 0423
DeepSeek · released Apr 24, 2026
Best input$0.637 / MTok
Best output$1.27 / MTok
Context1.05M
Providers16
Fastest measured0.51s° TTFT · 166 tok/s
Open weightsToolsReasoningStructured outputPrompt caching
Qwen3.8 27B
Qwen · released Aug 14, 2026
Best input$0.15 / MTok
Best output$2.00 / MTok
Context1M
Providers15
Fastest measured0.91s° TTFT · 33 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | STStreamLake | $0.637 | $1.27 | 2.2s° | 63° tok/s | 4/5 |
| DeepSeek V4 Pro 0423 | BABaidu | $0.646 | $1.29 | 1.1s° | 70° tok/s | 3/5 |
| DeepSeek V4 Pro 0423 | DIDigitalOcean | $0.87 | $1.74 | — | — | 5/5 |
| Qwen3.8 27B | DADarkbloom | $0.15 | $2.00 | — | — | — |
| Qwen3.8 27B | DEDekaLLM | $0.20 | $2.50 | — | — | — |
| Qwen3.8 27B | REReka | $0.214 | $2.55 | — | — | 4/5 |
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