DeepSeek V4.1 Flash (batch)
deepseek ↗ · 1049K ctx · 47 providers · updated 2026-11-03 06:15 UTC
The board shows this model's cheapest measured offer ($0.105/1M); the smaller figure under it is the mean of the 64 offers listed below ($0.387/1M). Add those up and divide — it matches. 24h token volume (10.2T) 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. Cross-check — Vercel AI Gateway: 9.7% of gateway token volume, 2.23% of spend (2026-11-03; share-of-traffic, daily, data CC BY 4.0).
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| Morph (fp8) | OpenRouter ↗ | $0.035 | $0.315 | 767ms | 71 | 100% | API-measured |
| Decart (fp4) | OpenRouter ↗ | $0.090 | $0.180 | 851ms | 124 | 100% | API-measured |
| Sail Research (fp4/us) | OpenRouter ↗ | $0.090 | $0.250 | 557ms | 71 | 100% | API-measured |
| Sail Research (fp4) | OpenRouter ↗ | $0.090 | $0.250 | 540ms | 53 | 100% | API-measured |
| sail | Pricebook (LiteLLM) ↗ | $0.090 | $0.300 | — | — | — | Official list |
| OpenInference (fp4) | OpenRouter ↗ | $0.035 | $0.500 | 767ms | 110 | 100% | API-measured |
| Relace (fp4) | OpenRouter ↗ | $0.035 | $0.500 | 411ms | 157 | 100% | API-measured |
| Wafer (us) | OpenRouter ↗ | $0.045 | $0.500 | 304ms | 205 | 100% | API-measured |
| DeepInfra (fp8/flex) | OpenRouter ↗ | $0.112 | $0.336 | 2789ms | 67 | 100% | API-measured |
| clf_ai_gateway | Pricebook (LiteLLM) ↗ | $0.120 | $0.480 | — | — | — | Official list |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.140 | $0.420 | — | — | — | Official list |
| DeepInfra (fp8) | OpenRouter ↗ | $0.140 | $0.420 | 635ms | 88 | 100% | API-measured |
| InferenceNet (us) | OpenRouter ↗ | $0.103 | $0.600 | 284ms | 100 | 100% | API-measured |
| InferenceNet (fp8) | OpenRouter ↗ | $0.103 | $0.600 | 264ms | 117 | 100% | API-measured |
| AtlasCloud (fp8) | OpenRouter ↗ | $0.135 | $0.540 | 706ms | 65 | 100% | API-measured |
| requesty | Requesty ↗ | $0.160 | $0.480 | — | — | — | API-measured |
| StreamLake (fp8) | OpenRouter ↗ | $0.147 | $0.588 | 1255ms | 66 | 100% | API-measured |
| CoreWeave (fp8) | OpenRouter ↗ | $0.130 | $0.650 | 585ms | 288 | 100% | API-measured |
| scx-ai | Pricebook (LiteLLM) ↗ | $0.150 | $0.600 | — | — | — | Official list |
| prism | Pricebook (LiteLLM) ↗ | $0.170 | $0.630 | — | — | — | Official list |
| Reka | OpenRouter ↗ | $0.105 | $0.840 | 495ms | 63 | 100% | API-measured |
| Mancer 2 (fp8) | OpenRouter ↗ | $0.150 | $0.750 | 714ms | 40 | 100% | API-measured |
| deepinfra | HuggingFace Router ↗ | $0.200 | $0.600 | 518ms | 111 | — | API-measured |
| Wafer (mxfp4) | OpenRouter ↗ | $0.190 | $0.650 | 285ms | 215 | 100% | API-measured |
| coralbricks | Pricebook (LiteLLM) ↗ | $0.010 | $1.20 | — | — | — | Official list |
| wandb | Pricebook (LiteLLM) ↗ | $0.200 | $0.650 | — | — | — | Official list |
| GMICloud (fp8) | OpenRouter ↗ | $0.180 | $0.720 | 2262ms | 153 | 100% | API-measured |
| DeepInfra (fp8/priority) | OpenRouter ↗ | $0.210 | $0.630 | 855ms | 68 | 100% | API-measured |
| Novita (fp8) | OpenRouter ↗ | $0.195 | $0.780 | 896ms | 99 | 100% | API-measured |
| Fireworks (spot) | OpenRouter ↗ | $0.210 | $0.840 | 593ms | 153 | 100% | API-measured |
| Phala | OpenRouter ↗ | $0.210 | $0.840 | 1212ms | 126 | 100% | API-measured |
| aiand | Pricebook (LiteLLM) ↗ | $0.300 | $0.600 | — | — | — | Official list |
| DigitalOcean | OpenRouter ↗ | $0.225 | $0.900 | 785ms | 188 | 100% | API-measured |
| kyma | Pricebook (LiteLLM) ↗ | $0.270 | $0.810 | — | — | — | Official list |
| PrimeIntellect | OpenRouter ↗ | $0.156 | $1.20 | 800ms | 163 | 100% | API-measured |
| Relace (fast) | OpenRouter ↗ | $0.300 | $0.900 | 452ms | 263 | 100% | API-measured |
| Makora (fp8) | OpenRouter ↗ | $0.260 | $1.17 | 573ms | 114 | 100% | API-measured |
| Crusoe (fp8) | OpenRouter ↗ | $0.290 | $1.20 | 568ms | 149 | 100% | API-measured |
| nebius | Pricebook (LiteLLM) ↗ | $0.300 | $1.20 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $0.300 | $1.20 | — | — | — | Official list |
Volume trend
Last 30 days: 3.4T → 10.2T (+198%); range 3.4T–10.3T 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-v4.1-flash.json. Free reuse requires attribution to tkx.org.
FAQ
How much does DeepSeek V4.1 Flash (batch) cost?
Cheapest measured offer right now: $0.035/1M input, $0.315/1M output via Morph (fp8) — across 47 tracked providers, refreshed hourly.
Who serves DeepSeek V4.1 Flash (batch)?
47 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is DeepSeek V4.1 Flash (batch) used?
DeepSeek V4.1 Flash (batch) routed 10.2T 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.