The board shows this model's cheapest measured offer ($0.087/1M); the smaller figure under it is the mean of the 49 offers listed below ($0.309/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| Relace (fast) | OpenRouter ↗ | $0.070 | $0.140 | 519ms | 95 | 100% | API-measured |
| Relace (fp4) | OpenRouter ↗ | $0.070 | $0.140 | 870ms | 33 | 100% | API-measured |
| deepinfra | HuggingFace Router ↗ | $0.060 | $0.180 | 423ms | 50 | — | API-measured |
| requesty | Requesty ↗ | $0.072 | $0.144 | — | — | — | API-measured |
| DeepInfra (fp8) | OpenRouter ↗ | $0.060 | $0.180 | 538ms | 60 | 100% | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.080 | $0.180 | — | — | — | Official list |
| sail | Pricebook (LiteLLM) ↗ | $0.090 | $0.180 | — | — | — | Official list |
| Wafer (us) | OpenRouter ↗ | $0.059 | $0.300 | 337ms | 142 | 100% | API-measured |
| Wafer (fast) | OpenRouter ↗ | $0.085 | $0.230 | 257ms | 147 | 100% | API-measured |
| PrimeIntellect (fp4) | OpenRouter ↗ | $0.090 | $0.230 | 554ms | 129 | 100% | API-measured |
| Reka | OpenRouter ↗ | $0.100 | $0.280 | 606ms | 89 | 100% | API-measured |
| DigitalOcean | OpenRouter ↗ | $0.119 | $0.238 | 584ms | 128 | 100% | API-measured |
| baseten | Pricebook (LiteLLM) ↗ | $0.130 | $0.260 | — | — | — | Official list |
| baseten | HuggingFace Router ↗ | $0.130 | $0.260 | 288ms | 76 | — | API-measured |
| BaseTen (fp8) | OpenRouter ↗ | $0.130 | $0.260 | 308ms | 136 | 100% | API-measured |
| BaseTen (fp32) | OpenRouter ↗ | $0.130 | $0.260 | 275ms | 108 | 100% | API-measured |
| Venice | OpenRouter ↗ | $0.130 | $0.260 | 424ms | 113 | 100% | API-measured |
| wandb | Pricebook (LiteLLM) ↗ | $0.130 | $0.280 | — | — | — | Official list |
| CoreWeave (fp8) | OpenRouter ↗ | $0.130 | $0.280 | 500ms | 80 | 100% | API-measured |
| nebius | Pricebook (LiteLLM) ↗ | $0.140 | $0.280 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $0.140 | $0.280 | — | — | — | Official list |
| Cohere | OpenRouter ↗ | $0.140 | $0.280 | 440ms | 138 | 100% | API-measured |
| Parasail (fp8) | OpenRouter ↗ | $0.140 | $0.280 | 652ms | 99 | 100% | API-measured |
| Sail Research (us) | OpenRouter ↗ | $0.150 | $0.300 | 737ms | 56 | 100% | API-measured |
| Sail Research (fp4) | OpenRouter ↗ | $0.150 | $0.300 | 980ms | 50 | 100% | API-measured |
| StreamLake (fp8) | OpenRouter ↗ | $0.132 | $0.396 | 3650ms | 29 | 100% | API-measured |
| Inceptron (fp4) | OpenRouter ↗ | $0.130 | $0.495 | 841ms | 50 | 100% | API-measured |
| inferenceapis | Pricebook (LiteLLM) ↗ | $0.190 | $0.380 | — | — | — | Official list |
| dashscope | Pricebook (LiteLLM) ↗ | $0.200 | $0.400 | — | — | — | Official list |
| qwencloud | Pricebook (LiteLLM) ↗ | $0.200 | $0.400 | — | — | — | Official list |
| qwen_ai_platform | Pricebook (LiteLLM) ↗ | $0.200 | $0.400 | — | — | — | Official list |
| Mancer 2 (fp8) | OpenRouter ↗ | $0.200 | $0.600 | 649ms | 70 | 100% | API-measured |
| fireworks_ai | Pricebook (LiteLLM) ↗ | $0.220 | $0.660 | — | — | — | Official list |
| SiliconFlow (fp8) | OpenRouter ↗ | $0.220 | $0.660 | 3185ms | 18 | 100% | API-measured |
| GMICloud (fp8) | OpenRouter ↗ | $0.286 | $0.858 | 2106ms | 60 | 100% | API-measured |
| scaleway | Pricebook (LiteLLM) ↗ | $0.400 | $0.800 | — | — | — | Official list |
| Alibaba | OpenRouter ↗ | $0.352 | $1.06 | 1544ms | 97 | 100% | API-measured |
| Alibaba (us-east-1) | OpenRouter ↗ | $0.374 | $1.12 | 1660ms | 98 | 100% | API-measured |
| Novita (fp8) | OpenRouter ↗ | $0.409 | $1.23 | 1097ms | 59 | 100% | API-measured |
| azure_ai | Pricebook (LiteLLM) ↗ | $0.440 | $1.32 | — | — | — | Official list |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.066 → $0.066 → $0.066 → $0.066 → $0.066 → $0.0054 → $0.0715 → $0.0753 → $0.09 → $0.09 → $0.09 → $0.09 → $0.0898 → $0.0388 → $0.0329 → $0.0329 → $0.0329 → $0.0394 → $0.0667 → $0.0667 → $0.0667 → $0.0667 → $0.0667 → $0.0667 → $0.0667 → $0.0686 → $0.0675 → $0.0667 → $0.0667 → $0.0667 → $0.0875
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/deepseek-v4-flash-0731.json. Free reuse requires attribution to tkx.org.
FAQ
How much does DeepSeek V4 Flash 0731 cost?
Cheapest measured offer right now: $0.07/1M input, $0.14/1M output via Relace (fast) — across 35 tracked providers, refreshed hourly.
Who serves DeepSeek V4 Flash 0731?
35 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of DeepSeek V4 Flash 0731 going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.