The board shows this model's cheapest measured offer ($0.113/1M); the smaller figure under it is the mean of the 7 offers listed below ($0.146/1M). Add those up and divide — it matches. Cross-check — Vercel AI Gateway: 11.41% of gateway token volume, —% of spend (2026-08-05; share-of-traffic, daily, data CC BY 4.0).
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| openrouter-best | OpenRouter | $0.090 | $0.180 | — | — | — | API-measured |
| deepinfra | HuggingFace Router | $0.090 | $0.180 | 473ms | 68 | — | API-measured |
| requesty | Requesty | $0.090 | $0.180 | — | — | — | API-measured |
| baseten | HuggingFace Router | $0.130 | $0.260 | 426ms | 199 | — | API-measured |
| together | HuggingFace Router | $0.140 | $0.280 | 739ms | 55 | — | API-measured |
| novita | HuggingFace Router | $0.140 | $0.280 | 542ms | 58 | — | API-measured |
| novita-ai | Novita AI | $0.140 | $0.280 | — | — | — | API-measured |
Price trend
Cheapest blended price, last 6 days (USD/1M): $0.175 → $0.1125 → $0.1125 → $0.1125 → $0.1125 → $0.1125
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: $0.09/1M input, $0.18/1M output via openrouter-best — across 6 tracked providers, refreshed hourly.
Who serves DeepSeek V4 Flash 0731?
6 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of DeepSeek V4 Flash 0731 going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.