The board shows this model's cheapest measured offer ($0.544/1M); the smaller figure under it is the mean of the 35 offers listed below ($1.89/1M). Add those up and divide — it matches. 24h token volume (293B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| tencent | Pricebook (LiteLLM) ↗ | $0.435 | $0.870 | — | — | — | Official list |
| StreamLake (fp8) | OpenRouter ↗ | $0.686 | $1.37 | 2047ms | 37 | 99.7% | API-measured |
| Baidu (fp8) | OpenRouter ↗ | $0.695 | $1.39 | 1030ms | 55 | 100.0% | API-measured |
| 0g-teetls | 0G Router ↗ | $0.792 | $2.38 | — | — | — | API-measured |
| GMICloud (fp8) | OpenRouter ↗ | $0.957 | $1.91 | 2181ms | 36 | 99.6% | API-measured |
| fireworks_ai | Pricebook (LiteLLM) ↗ | $1.20 | $1.20 | — | — | — | Official list |
| DigitalOcean | OpenRouter ↗ | $1.04 | $2.09 | 742ms | 41 | 100.0% | API-measured |
| wandb | Pricebook (LiteLLM) ↗ | $1.15 | $2.55 | — | — | — | Official list |
| Cloudflare | OpenRouter ↗ | $1.15 | $2.55 | 1337ms | 42 | 99.0% | API-measured |
| deepinfra | HuggingFace Router ↗ | $1.30 | $2.60 | 445ms | 34 | — | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $1.30 | $2.60 | — | — | — | Official list |
| DeepInfra (fp8) | OpenRouter ↗ | $1.30 | $2.60 | 1238ms | 35 | 99.8% | API-measured |
| Alibaba (fp8) | OpenRouter ↗ | $1.42 | $2.83 | 1653ms | 42 | 100% | API-measured |
| SiliconFlow (fp8) | OpenRouter ↗ | $1.50 | $3.13 | 1725ms | 43 | 99.8% | API-measured |
| deepseek | Pricebook (LiteLLM) ↗ | $1.32 | $3.96 | — | — | — | Official list |
| openrouter | Pricebook (LiteLLM) ↗ | $1.60 | $3.20 | — | — | — | Official list |
| novita | Pricebook (LiteLLM) ↗ | $1.60 | $3.20 | — | — | — | Official list |
| novita | HuggingFace Router ↗ | $1.60 | $3.20 | 729ms | 68 | — | API-measured |
| novita-ai | Novita AI ↗ | $1.60 | $3.20 | — | — | — | API-measured |
| Novita (fp8) | OpenRouter ↗ | $1.60 | $3.20 | 1658ms | 90 | 99.6% | API-measured |
| Venice | OpenRouter ↗ | $1.65 | $3.30 | 1564ms | 42 | 96.3% | API-measured |
| AtlasCloud (fp4) | OpenRouter ↗ | $1.68 | $3.38 | 1312ms | 39 | 99.9% | API-measured |
| aihubmix | Pricebook (LiteLLM) ↗ | $1.69 | $3.38 | — | — | — | Official list |
| azure_ai | Pricebook (LiteLLM) ↗ | $1.74 | $3.48 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $1.74 | $3.48 | — | — | — | Official list |
| baseten | HuggingFace Router ↗ | $1.74 | $3.48 | 2905ms | 59 | — | API-measured |
| BaseTen (fp4) | OpenRouter ↗ | $1.74 | $3.48 | 493ms | 100 | 100.0% | API-measured |
| Parasail (fp8) | OpenRouter ↗ | $1.74 | $3.48 | 807ms | 50 | 99.8% | API-measured |
| nebius | Pricebook (LiteLLM) ↗ | $1.75 | $3.50 | — | — | — | Official list |
| requesty | Requesty ↗ | $1.75 | $3.50 | — | — | — | API-measured |
| NextBit (fp8) | OpenRouter ↗ | $1.91 | $3.83 | 4863ms | 35 | 98.3% | API-measured |
| Azure (us) | OpenRouter ↗ | $1.91 | $3.83 | 1451ms | 52 | 99.9% | API-measured |
| dashscope | Pricebook (LiteLLM) ↗ | $2.40 | $4.80 | — | — | — | Official list |
| qwencloud | Pricebook (LiteLLM) ↗ | $2.40 | $4.80 | — | — | — | Official list |
| qwen_ai_platform | Pricebook (LiteLLM) ↗ | $2.40 | $4.80 | — | — | — | Official list |
Volume trend
Last 30 days: 367B → 293B (-20%); range 244B–486B tokens/day. Source: OpenRouter public rankings; refreshed hourly.
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-pro.json. Free reuse requires attribution to tkx.org.
About
Deepseek-v4-pro is an AI model, a machine-learning system designed for language understanding and generation tasks. It is served by multiple inference providers on AI model marketplaces under the organization tag "deepseek".
AI-generated summary from public information — is this yours?
FAQ
How much does deepseek-v4-pro cost?
Cheapest measured offer right now: $0.435/1M input, $0.87/1M output via tencent — across 27 tracked providers, refreshed hourly.
Who serves deepseek-v4-pro?
27 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is deepseek-v4-pro used?
deepseek-v4-pro routed 293B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.