DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window.
text → text · made by DeepSeek
Sold by 44 ways
| Seller | Lane | Rate |
|---|---|---|
| DigitalOcean cloud | standard | $0.068per Mtok in$0.17per Mtok out$0.017per Mtok cachedmodels.dev · read 2026-09-16 |
| Writer api | standard | $0.09per Mtok in$0.18per Mtok outdev.writer.com · read 2026-08-25 |
| Microsoft Azure AI cloud | standard | $0.19per Mtok in$0.51per Mtok out$0.028per Mtok cachedmodels.dev · read 2026-09-16 |
| DeepSeek api | standard | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedapi-docs.deepseek.com · read 2026-08-24 |
| Nous Research aggregator | standard | $0.05per Mtok in$0.14per Mtok out$0.014per Mtok cachedinference-api.nousresearch.com · read 2026-09-13 |
| OpenRouter 18 ways | $0.089per Mtok in$0.18per Mtok out$0.018per Mtok cached | |
| OpenRouter aggregator | open-inference/fp8 | $0.05per Mtok in$0.14per Mtok out$0.014per Mtok cachedopenrouter.ai · read 2026-09-13 |
| OpenRouter aggregator | wafer | $0.07per Mtok in$0.25per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-09-16 |
| OpenRouter aggregator | standard | $0.089per Mtok in$0.18per Mtok out$0.018per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | streamlake/fp8 | $0.089per Mtok in$0.18per Mtok out$0.018per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | deepinfra/fp8 | $0.09per Mtok in$0.18per Mtok out$0.018per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | sail-research/fp4 | $0.09per Mtok in$0.18per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | gmicloud/fp8 | $0.091per Mtok in$0.18per Mtok out$0.018per Mtok cachedopenrouter.ai · read 2026-09-08 |
| OpenRouter aggregator | venice | $0.097per Mtok in$0.19per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-09-13 |
| OpenRouter aggregator | digitalocean | $0.098per Mtok in$0.2per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | siliconflow/fp8 | $0.13per Mtok in$0.28per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | alibaba/fp8 | $0.13per Mtok in$0.27per Mtok out$0.027per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | atlas-cloud/fp4 | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | baidu/fp8 | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-09-14 |
| OpenRouter aggregatornot on the seller's list today | coreweave/fp8 | $0.14per Mtok in$0.28per Mtok out$0.07per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | novita/fp8 | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp8 | $0.14per Mtok in$0.28per Mtok out$0.07per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nextbit/fp8 | $0.15per Mtok in$0.35per Mtok out$0.035per Mtok cachedopenrouter.ai · read 2026-09-07 |
| OpenRouter aggregator | mancer/fp8 | $0.19per Mtok in$0.5per Mtok outopenrouter.ai · read 2026-09-09 |
| OpenRouter aggregator | phala | $0.2per Mtok in$0.4per Mtok out$0.07per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | azure/us | $0.21per Mtok in$0.56per Mtok out$0.031per Mtok cachedopenrouter.ai · read 2026-08-28 |
| OpenRouter aggregatornot on the seller's list today | cloudflare | $0.44per Mtok in$1.32per Mtok out$0.014per Mtok cachedopenrouter.ai · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.06per Mtok in$0.1per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Requesty 0 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 aggregatornot on the seller's list today | deepinfra | $0.072per Mtok in$0.14per Mtok out$0.014per Mtok cachedrouter.requesty.ai · read 2026-08-30 |
| Requesty aggregatornot on the seller's list today | doubleword flex | $0.09per Mtok in$0.18per Mtok outrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | doubleword | $0.1per Mtok in$0.2per Mtok outrouter.requesty.ai · read 2026-08-30 |
| Requesty aggregatornot on the seller's list today | novita | $0.14per Mtok in$0.28per Mtok outrouter.requesty.ai · read 2026-08-28 |
| Avian aggregator | standard | $0.081per Mtok in$0.16per Mtok out$0.017per Mtok cachedapi.avian.io · read 2026-09-16 |
| DeepInfra aggregator | standard | $0.09per Mtok in$0.18per Mtok out$0.018per Mtok cachedapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 3 ways | $0.14per Mtok in$0.28per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.09per Mtok in$0.18per 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 | novita | $0.14per Mtok in$0.28per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $0.13per Mtok in$0.26per Mtok out$0.028per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Nebius Token Factory 0 ways | $0.14per Mtok in$0.28per Mtok out | |
| Nebius Token Factory aggregatornot on the seller's list today | standard | $0.14per Mtok in$0.28per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Novita AI aggregator | standard | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedapi.novita.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedmodels.dev · read 2026-09-16 |
| Inference.net aggregator | standard | $0.23per Mtok in$0.62per Mtok out$0.0028per Mtok cachedapi.inference.net · read 2026-09-16 |
| PPIO aggregator | standard | $3per Mtok in$9per Mtok outapi.ppinfra.com · read 2026-09-16 |
Measured 14 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 13thof 32 | AIME 2026 | Accuracy (± 95% CI) (max) | 95.83 |
| 22ndof 128 | LMArena · WebDev | Score (Elo) (high) | 1580 |
| 36thof 46 | LMArena · Agent | Net Improvement (%) (high) | 1.8 |
| 44thof 161 | Dtbench — Epoch AI | Accuracy (max) | 86.4 |
| 52ndof 123 | Lmca — Epoch AI | Score (max) | 35.88 |
| 61stof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.463 |
| 67thof 121 | Webdev arena — Epoch AI | Arena Score (high) | 1431.07 |
| 73rdof 112 | Ale bench — Epoch AI | Performance (high) | 678.2 |
| 75thof 177 | Critpt — Epoch AI | Accuracy (max) | 7.143 |
| 86thof 170 | Weirdml — Epoch AI | Accuracy (max) | 45.63 |
| 87thof 402 | LMArena · Text | Score (Elo) (high) | 1438 |
| 91stof 168 | Scicode — Epoch AI | Score (max) | 44.907 |
| 125thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index | 19 |
| 293rdof 656 | Epoch capabilities index — Epoch AI | ECI Score (max) | 146.26 |
About
DeepSeek V4 Flash — a text model from DeepSeek, sold by 16 companies from $0.05 in and $0.14 out per million tokens, placed 22nd of 128 on LMArena · WebDev.
It takes text and returns text, with a context window of 1,000,000 tokens. It was published in April 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, code and agents. Sixteen companies sell it. The cheapest is $0.05 in and $0.14 out per million tokens at Nous Research. Beside the standard rate there are separately routed and regional lanes. It has been measured on 14 boards, and stands best at 22nd of 128 on LMArena · WebDev.
Every current figure
- Maker
- DeepSeek
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 1,000,000 tokens
- Published
- April 2026
- Knowledge to
- May 2025
- Parameters
- 291 billion
- Licence
- not read
- Sellers
- 16
- Price
- $0.05 in and $0.14 out per million tokens — Nous Research
- Boards
- 14
- Best place
- 22nd of 128 — LMArena · WebDev
Known as 12 names
DeepSeek-v4-Flash (Max)Deepseek V4 Flash (High) (20260731)deepseek-v4-flash-highV4 Flashdeepseek-ai/DeepSeek-V4-Flashdeepseek-v4-flashdeepseek/deepseek-v4-flashdeepinfra/deepseek-ai/DeepSeek-V4-Flashdeepinfra/deepseek-ai/DeepSeek-V4-Flash:flexdoubleword/deepseek-v4-flashdoubleword/deepseek-v4-flash:flexnovita/deepseek/deepseek-v4-flash