DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
Text
9 gateways
4.40x price spread
Where you can run it
| Gateway | Its id | Context | Max output | Input / Mtok | Output / Mtok |
|---|---|---|---|---|---|
| Baseten | deepseek-ai/DeepSeek-V4-Flash-0731 |
1M | 384K | $0.130 | $0.260 |
| Cloudflare AI Gateway | deepseek/deepseek-v4-flash-0731 |
— | — | — | — |
| Morph | deepseek/deepseek-v4-flash-0731 |
1M | 1M | $0.142 | $0.400 |
| NanoGPT Cheapest input | deepseek/deepseek-v4-flash-0731 |
1M | 131.1K | $0.050 | $0.160 |
| OpenRouter | deepseek/deepseek-v4-flash-0731 |
1M | 943.7K | $0.119 | $0.238 |
| OrcaRouter | deepseek/deepseek-v4-flash-0731 |
1M | 384K | $0.220 | $0.660 |
| Requesty | sail/deepseek-v4-flash-0731 |
1M | 384K | $0.090 | $0.180 |
| Sail | deepseek-ai/DeepSeek-V4-Flash-0731 |
— | — | — | — |
| Vercel AI Gateway | deepseek/deepseek-v4-flash-0731 |
1M | 384K | $0.076 | $0.153 |
Prices are US dollars per million tokens, as published in each gateway's own catalog at the last crawl. A dash means that gateway publishes no value — not that it is free. Rows differ because gateways set their own markup, and some let you bring your own provider key.
- Canonical id
deepseek/deepseek-v4-flash-0731- Vendor
- DeepSeek
- Type
- Text
- Gateways serving it
- BasetenCloudflareMorphNanoGPTOpenRouterOrcaRouterRequestySailVercel
- Batch pricing
- deepseek/deepseek-v4-flash-0731:batch
- Largest context window
- 1M tokens
- Input price range
- $0.050 – $0.220 / Mtok
- Price spread
- 4.40x between cheapest and dearest gateway
- Accepts
- Text
- Returns
- Text
- Cataloged since
History
What changed for DeepSeek V4 Flash 0731
Recorded by the daily catalog crawl — when gateways picked this model up, dropped it, or repriced it.
- NanoGPT raised input 12.5% to $0.050 and output 20% to $0.160 on DeepSeek V4 Flash 0731
- Experiential Labs added deepseek-v4-flash-0731
- SayGM added DeepSeek-V4-Flash-0731
- Cheaper Inference added deepseek-v4-flash-0731
- Concentrate added DeepSeek V4 Flash 0731
- Ramp Router added DeepSeek V4 Flash 0731 (Baseten)
- NanoGPT cut input 11.1% to $0.044 and output 16.7% to $0.133 on DeepSeek V4 Flash 0731
- Experiential Labs added deepseek-v4-flash-0731
- SayGM added DeepSeek-V4-Flash-0731
- Cheaper Inference added deepseek-v4-flash-0731
- Concentrate added DeepSeek V4 Flash 0731
- Ramp Router added DeepSeek V4 Flash 0731 (Baseten)
- Experiential Labs added deepseek-v4-flash-0731
- SayGM added DeepSeek-V4-Flash-0731
- Cheaper Inference added deepseek-v4-flash-0731