DeepSeek V4 Flash (0731)
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.
text → text · made by DeepSeek
Sold by 66 ways
| Seller | Lane | Rate |
|---|---|---|
| DigitalOcean cloud | standard | $0.08per Mtok in$0.25per Mtok out$0.025per Mtok cachedmodels.dev · read 2026-09-16 |
| Databricks cloud | standard | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cached$0.14per Mtok cache writeraw.githubusercontent.com · read 2026-09-16 |
| Microsoft Azure AI cloud | standard | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| OpenRouter 32 ways | $0.055per Mtok in$0.11per Mtok out$0.011per Mtok cached | |
| OpenRouter aggregatornot on the seller's list today | open-inference/fp4 | $0.03per Mtok in$0.1per Mtok out$0.007per Mtok cachedopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | open-inference/fp8 | $0.04per Mtok in$0.1per Mtok out$0.01per Mtok cachedopenrouter.ai · read 2026-09-14 |
| OpenRouter aggregator | inceptron/fp4 | $0.055per Mtok in$0.17per Mtok out$0.0087per Mtok cachedopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregator | standard | $0.055per Mtok in$0.11per Mtok out$0.011per Mtok cachedopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregator | relace/fp4 | $0.055per Mtok in$0.11per Mtok out$0.011per Mtok cachedopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregator | streamlake/fp8 | $0.057per Mtok in$0.17per Mtok out$0.0018per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | deepinfra/fp8 | $0.06per Mtok in$0.18per Mtok out$0.015per Mtok cachedopenrouter.ai · read 2026-09-07 |
| OpenRouter aggregatornot on the seller's list today | akashml/fp8 | $0.065per Mtok in$0.18per Mtok out$0.016per Mtok cachedopenrouter.ai · read 2026-08-31 |
| OpenRouter aggregator | sail-research/fp4 | $0.074per Mtok in$0.34per Mtok out$0.023per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | sail-research/us | $0.074per Mtok in$0.34per Mtok out$0.023per Mtok cachedopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregatornot on the seller's list today | ambient/fp4 | $0.08per Mtok in$0.18per Mtok out$0.016per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | makora | $0.09per Mtok in$0.2per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-08-28 |
| OpenRouter aggregator | wafer/fast | $0.1per Mtok in$0.25per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-09-03 |
| OpenRouter aggregator | batch | $0.11per Mtok in$0.33per Mtok out$0.0035per Mtok cachedopenrouter.ai · read 2026-09-09 |
| OpenRouter aggregator | reka/fp4 | $0.11per Mtok in$0.66per Mtok out$0.007per Mtok cachedopenrouter.ai · read 2026-09-02 |
| OpenRouter aggregator | digitalocean | $0.12per Mtok in$0.24per Mtok out$0.024per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | baseten/fp8 | $0.13per Mtok in$0.26per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | coreweave/fp8 | $0.13per Mtok in$0.28per Mtok out$0.07per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp8 | $0.14per Mtok in$0.28per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | together | $0.14per Mtok in$0.28per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | morph/bf16 | $0.14per Mtok in$0.4per Mtok out$0.036per Mtok cachedopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregator | venice | $0.17per Mtok in$0.35per Mtok out$0.035per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | mancer/fp8 | $0.2per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregatornot on the seller's list today | io-net/fp8 | $0.22per Mtok in$0.49per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | fireworks | $0.22per Mtok in$0.66per Mtok out$0.007per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | siliconflow/fp8 | $0.22per Mtok in$0.66per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | gmicloud/fp4 | $0.29per Mtok in$0.86per Mtok out$0.0091per Mtok cachedopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | gmicloud/fp8 | $0.29per Mtok in$0.86per Mtok out$0.0091per Mtok cachedopenrouter.ai · read 2026-09-10 |
| OpenRouter aggregator | alibaba | $0.35per Mtok in$1.06per Mtok out$0.035per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nextbit/fp8 | $0.35per Mtok in$1.06per Mtok out$0.012per Mtok cachedopenrouter.ai · read 2026-09-08 |
| OpenRouter aggregator | novita/fp8 | $0.41per Mtok in$1.23per Mtok out$0.026per Mtok cachedopenrouter.ai · read 2026-09-05 |
| OpenRouter aggregator | atlas-cloud/fp4 | $0.44per Mtok in$1.32per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | baidu/fp8 | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | cloudflare | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | deepseek | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedopenrouter.ai · read 2026-09-07 |
| OpenRouter aggregator | phala | $0.44per Mtok in$1.32per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-30 |
| Nous Research 2 ways | $0.04per Mtok in$0.1per Mtok out$0.01per Mtok cached | |
| Nous Research aggregator | standard | $0.04per Mtok in$0.1per Mtok out$0.01per Mtok cachedinference-api.nousresearch.com · read 2026-09-15 |
| Nous Research aggregator | batch | $0.11per Mtok in$0.33per Mtok out$0.0035per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| DeepInfra aggregator | standard | $0.06per Mtok in$0.18per Mtok outapi.deepinfra.com · read 2026-09-07 |
| Hugging Face Inference Providers 5 ways | $0.14per Mtok in$0.28per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.06per Mtok in$0.18per Mtok outrouter.huggingface.co · read 2026-09-07 |
| Hugging Face Inference Providers aggregator | baseten | $0.13per Mtok in$0.26per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.14per Mtok in$0.28per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | together | $0.14per Mtok in$0.28per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.44per Mtok in$1.32per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Requesty 6 ways | $0.065per Mtok in$0.13per Mtok out$0.013per Mtok cached | |
| Requesty aggregatornot on the seller's list today | deepinfra flex | $0.065per Mtok in$0.13per Mtok out$0.013per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | deepinfra | $0.09per Mtok in$0.18per Mtok out$0.018per Mtok cachedrouter.requesty.ai · read 2026-09-16 |
| Requesty aggregator | novita | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | fireworks | $0.22per Mtok in$0.66per Mtok out$0.007per Mtok cachedrouter.requesty.ai · read 2026-09-09 |
| Requesty aggregator | tensorx | $0.25per Mtok in$0.3per Mtok out$0.06per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | sference | $0.28per Mtok in$0.56per Mtok out$0.07per Mtok cachedrouter.requesty.ai · read 2026-09-09 |
| Requesty aggregator | deepseek | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Vercel AI Gateway aggregator | standard | $0.076per Mtok in$0.15per Mtok out$0.014per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Baseten aggregator | standard | $0.13per Mtok in$0.26per Mtok out$0.13per Mtok cachedbaseten.co · read 2026-08-25 |
| Nebius Token Factory aggregator | standard | $0.14per Mtok in$0.28per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Together AI aggregator | standard | $0.14per Mtok in$0.28per Mtok out$0.03per Mtok cacheddocs.together.ai · read 2026-08-24 |
| Venice AI aggregator | standard | $0.17per Mtok in$0.35per Mtok out$0.035per Mtok cachedmodels.dev · read 2026-09-16 |
| Fireworks AI 2 ways | $0.22per Mtok in$0.66per Mtok out$0.007per Mtok cached | |
| Fireworks AI aggregator | standard | $0.22per Mtok in$0.66per Mtok out$0.007per Mtok cacheddocs.fireworks.ai · read 2026-08-24 |
| Fireworks AI aggregator | priority | $0.28per Mtok in$0.82per Mtok out$0.0088per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Cloudflare aggregator | standard | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cacheddevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | sandbox | $0.44per Mtok in$1.32per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Novita AI aggregator | standard | $0.44per Mtok in$1.32per Mtok out$0.028per Mtok cachedapi.novita.ai · read 2026-08-25 |
| Inference.net aggregator | standard | $0.53per Mtok in$1.58per Mtok out$0.017per Mtok cachedapi.inference.net · read 2026-09-16 |
| PPIO aggregator | standard | $3per Mtok in$9per Mtok outapi.ppinfra.com · read 2026-09-16 |
Measured 35 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 14thof 64 | Proofbench — Epoch AI | Accuracy | 56 |
| 16thof 121 | Webdev arena — Epoch AI | Arena Score (high) | 1579.1 |
| 18thof 127 | Mystery game puzzles — Epoch AI | mean_score (max) | 34 |
| 23rdof 112 | Ale bench — Epoch AI | Performance (max) | 1306.08 |
| 24thof 30 | Frontiercode — Epoch AI | Main score | 0.188 |
| 26thof 161 | Dtbench — Epoch AI | Accuracy (max) | 90.93 |
| 28thof 313 | GPQA Diamond | mean_score (max) | 91.035 |
| 28thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.611 |
| 31stof 106 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (max) | 57.544 |
| 32ndof 123 | Lmca — Epoch AI | Score (max) | 41.73 |
| 34thof 143 | Artificial Analysis · Agentic Index | Index | 41.7 |
| 37thof 62 | Frontiermath tier 4 v2 — Epoch AI | mean_score (max) | 24.39 |
| 41stof 290 | OTIS Mock AIME 2024-2025 | mean_score (max) | 94.444 |
| 42ndof 222 | Chess puzzles — Epoch AI | mean_score (max) | 33 |
| 42ndof 109 | Design Arena · svg (models) | Elo | 1212 |
| 42ndof 170 | Weirdml — Epoch AI | Accuracy (max) | 62.96 |
| 46thof 184 | Artificial Analysis · Coding Index | Index | 69.1 |
| 49thof 177 | Critpt — Epoch AI | Accuracy (max) | 16.571 |
| 51stof 80 | Simpleqa verified — Epoch AI | mean_score (max) | 33.634 |
| 52ndof 216 | ARC-AGI-2 (Public Eval) | Score (%) (max) | 63.89 |
| 52ndof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index (max) | 35 |
| 53rdof 205 | ARC-AGI-1 (Public Eval) | Score (%) (max) | 94.75 |
| 53rdof 147 | Design Arena · 3d (models) | Elo | 1237 |
| 54thof 232 | ARC-AGI-2 (Semi-Private) | Score (%) (max) | 61.39 |
| 55thof 150 | Design Arena · uicomponent (models) | Elo | 1252 |
| 56thof 155 | Design Arena · gamedev (models) | Elo | 1233 |
| 57thof 162 | Design Arena · website (models) | Elo | 1251 |
| 58thof 230 | ARC-AGI-1 (Semi-Private) | Score (%) (max) | 89 |
| 58thof 156 | Design Arena · codecategories (models) | Elo | 1246 |
| 62ndof 227 | Arc agi 2 — Epoch AI | Score (max) | 61.389 |
| 64thof 168 | Scicode — Epoch AI | Score (max) | 49.884 |
| 66thof 244 | Arc agi — Epoch AI | Score (max) | 89 |
| 78thof 152 | Design Arena · dataviz (models) | Elo | 1197 |
| 82ndof 92 | Design Arena · asciiart (models) | Elo | 1110 |
| 151stof 656 | Epoch capabilities index — Epoch AI | ECI Score (max) | 154.46 |
About
DeepSeek V4 Flash (0731) — a text model from DeepSeek, sold by 18 companies from $0.04 in and $0.1 out per million tokens, placed 28th of 313 on GPQA Diamond.
It takes text and returns text, with a context window of 1,000,000 tokens. It was published in July 2026, trained on material up to May 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Eighteen companies sell it. The cheapest is $0.04 in and $0.1 out per million tokens at Nous Research. Beside the standard rate there are faster, separately routed, batch and regional lanes. It has been measured on 35 boards, and stands best at 28th of 313 on GPQA Diamond.
Every current figure
- Maker
- DeepSeek
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 1,000,000 tokens
- Published
- July 2026
- Knowledge to
- May 2025
- Parameters
- 304 billion
- Licence
- not read
- Sellers
- 18
- Maker's own price
- not read
- Price
- $0.04 in and $0.1 out per million tokens — Nous Research
- Boards
- 35
- Best place
- 28th of 313 — GPQA Diamond
Known as 11 names
DeepSeek V4 Flash 0731 (max)V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731@cf/deepseek-ai/deepseek-v4-flash-0731fireworks/deepseek-v4-flash-0731deepseek/deepseek-v4-flash-0731deepinfra/deepseek-v4-flash-0731deepinfra/deepseek-v4-flash-0731:flexnovita/deepseek/deepseek-v4-flash-0731sference/deepseek-v4-flash-0731tensorx/deepseek-v4-flash-0731