DeepSeek V4 Flash 0731 pricing across providers
Across tracked provider offerings, input runs $0.045–$0.440 per million tokens and output $0.090–$1.32 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Baidu at $0.0038 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 26 of 27 offerings publish a cache-read rate; 19 of 27 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to DeepSeek V4 Flash 0731
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for DeepSeek V4 Flash 0731
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Baidu promo | fp8 | $0.054 | $0.161 | $0.0017 | $0.0038 | 100.00% |
| Streamlake promo | fp8 | $0.132 | $0.396 | $0.0042 | $0.0094 | 100.00% |
| Engy | — | $0.045 | $0.090 | $0.0090 | $0.010 | — |
| Singularity | — | $0.200 | $0.500 | $0.0070 | $0.014 | — |
| DeepInfra | — | $0.060 | $0.180 | $0.015 | $0.017 | — |
| GMI Cloud promo | fp8 | $0.286 | $0.858 | $0.0091 | $0.020 | 100.00% |
| Alibaba | unknown | $0.176 | $0.528 | $0.018 | $0.024 | 100.00% |
| Digitalocean | unknown | $0.119 | $0.238 | $0.024 | $0.027 | 100.00% |
| Relace | fp4 | $0.051 | $0.149 | $0.028 | $0.029 | 100.00% |
| Runanywhere | fp8 | $0.440 | $1.32 | $0.014 | $0.031 | — |
| Cloudflare | unknown | $0.440 | $1.32 | $0.014 | $0.031 | 100.00% |
| Phala promo | unknown | $0.308 | $0.924 | $0.020 | $0.031 | — |
| Inceptron | fp4 | $0.130 | $0.409 | $0.027 | $0.031 | 100.00% |
| Baseten | fp8 | $0.130 | $0.260 | $0.028 | $0.032 | 100.00% |
| Venice | unknown | $0.130 | $0.260 | $0.028 | $0.032 | 100.00% |
| SiliconFlow | fp8 | $0.220 | $0.660 | $0.028 | $0.036 | 100.00% |
| Novita promo | fp8 | $0.409 | $1.23 | $0.026 | $0.042 | 100.00% |
| Reka | unknown | $0.100 | $0.280 | $0.040 | $0.043 | 100.00% |
| Atlascloud | fp4 | $0.440 | $1.32 | $0.028 | $0.045 | 100.00% |
| Sail Research | fp4 | $0.150 | $0.300 | $0.042 | $0.046 | 100.00% |
| Wafer | nvfp4 | $0.046 | $0.300 | $0.045 | $0.046 | — |
| Parasail | fp8 | $0.140 | $0.280 | $0.050 | $0.053 | 100.00% |
| Hyper | — | $0.440 | $1.32 | $0.044 | $0.060 | — |
| Coreweave | fp8 | $0.130 | $0.280 | $0.070 | $0.073 | 100.00% |
| Cohere | unknown | $0.140 | $0.280 | $0.070 | $0.073 | 100.00% |
| Sference | — | $0.280 | $0.560 | $0.070 | $0.078 | — |
| Mancer 2 | fp8 | $0.200 | $0.600 | — | $0.202 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.