DeepSeek V4 Flash 0731 — provider prices
29 providers offer this model. Cheapest input is $0.059, priciest is $0.440 — a 7.5x spread.
Providers
29
Cheapest
$0.059
Priciest
$0.440
Spread
7.5x
All quotes, cheapest first
| Provider | Input | Output | Context | Quantization |
|---|---|---|---|---|
| Wafer | $0.059 | $0.300 | 1049K | nvfp4 |
| DeepInfra | $0.060 | $0.180 | 1049K | FP8 — good balance |
| Relace | $0.070 | $0.140 | 1049K | FP4 — lowest precision, expect quality loss |
| Relace | $0.070 | $0.140 | 1049K | FP4 — lowest precision, expect quality loss |
| Wafer | $0.085 | $0.230 | 1049K | nvfp4 |
| PrimeIntellect | $0.090 | $0.230 | 1049K | FP4 — lowest precision, expect quality loss |
| Reka | $0.100 | $0.280 | 262K | not disclosed |
| DigitalOcean | $0.119 | $0.238 | 1049K | not disclosed |
| BaseTen | $0.130 | $0.260 | 1049K | FP8 — good balance |
| BaseTen | $0.130 | $0.260 | 1049K | fp32 |
| Venice | $0.130 | $0.260 | 1000K | not disclosed |
| CoreWeave | $0.130 | $0.280 | 262K | FP8 — good balance |
| Inceptron | $0.130 | $0.495 | 1049K | FP4 — lowest precision, expect quality loss |
| StreamLake | $0.132 | $0.396 | 1024K | FP8 — good balance |
| Cohere | $0.140 | $0.280 | 1049K | not disclosed |
| Parasail | $0.140 | $0.280 | 1049K | FP8 — good balance |
| Sail Research | $0.150 | $0.300 | 1049K | FP4 — lowest precision, expect quality loss |
| Sail Research | $0.150 | $0.300 | 1049K | FP4 — lowest precision, expect quality loss |
| Alibaba | $0.176 | $0.528 | 1000K | not disclosed |
| Alibaba | $0.187 | $0.561 | 1000K | not disclosed |
| Mancer 2 | $0.200 | $0.600 | 1049K | FP8 — good balance |
| SiliconFlow | $0.220 | $0.660 | 1049K | FP8 — good balance |
| GMICloud | $0.286 | $0.858 | 1049K | FP8 — good balance |
| Phala | $0.308 | $0.924 | 1049K | not disclosed |
| Novita | $0.409 | $1.23 | 1049K | FP8 — good balance |
| Chutes | $0.440 | $1.32 | 1049K | FP8 — good balance |
| Baidu | $0.440 | $1.32 | 1049K | FP8 — good balance |
| AtlasCloud | $0.440 | $1.32 | 1049K | FP4 — lowest precision, expect quality loss |
| Cloudflare | $0.440 | $1.32 | 1049K | not disclosed |
USD per million tokens. Verified 2026-11-04. Source: OpenRouter public API.
Cheapest is Wafer at $0.059 input.
Check the quantization column before switching: undisclosed or FP4 quotes can produce
noticeably worse output on reasoning and code tasks.
Related
All DeepSeek models · Price ranges · Cost calculator · Official pricing