DeepSeek V4.1 Flash: API pricing, providers and specs
DeepSeek V4.1 Flash is a text model by DeepSeek. 39 providers serve it, from $0.03 to $2.40 /1M; the lowest price is at UnoRouter.
How DeepSeek V4.1 Flash compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.03 /1M, its lowest price undercuts 99% of comparable models (median $1.10).
- Its 1.05M-token context window is larger than 83% of them (median 262K), about 1570 pages of text.
- On LMArena's WebDev board it ranks #10 of the 64 comparable models scored there.
- 39 providers serve it; 99% of comparable models have fewer.
- Its weights are open under the MIT license: commercial use allowed.
DeepSeek V4.1 Flash prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 Nvidia | Free/1M | Free/1M | — | — |
 UnoRouter | $0.007/1M | $0.03/1M | — | — |
| ZenMux | $0.075/1M | $0.30/1M | $0.002/1M | 1M |
| Vercel AI Gateway | $0.075/1M | From$0.30/1M | $0.002/1M | 1.05M |
 Kenari | $0.152/1M | $0.304/1M | $0.004/1M | — |
 Deep Infra | $0.14/1M | From$0.42/1M | $0.004/1M | — |
 FastRouter | $0.14/1M | $0.42/1M | $0.004/1M | 1.05M |
 CometAPI | $0.12/1M | From$0.48/1M | — | — |
 AIHubMix | $0.141/1M | $0.563/1M | $0.003/1M | 1M |
 CrazyRouter | $0.149/1M | $0.597/1M | — | — |
 Requesty | $0.15/1M | From$0.60/1M | $0.01/1M | 1.05M |
 Hugging Face | $0.20/1M | From$0.60/1M | — | — |
| DevPass (LLM Gateway) | $0.20/1M | From$0.60/1M | $0.006/1M | — |
| BytePlus | $0.15/1M | From$0.60/1M | $0.003/1M | — |
 OrcaRouter | $0.15/1M | From$0.60/1M | $0.003/1M | 1.05M |
 Cortecs | $0.201/1M | $0.603/1M | $0.004/1M | — |
| APIMart | $0.229/1M | $0.914/1M | — | — |
 Boundless | $0.20/1M | $1/1M | $0.01/1M | — |
| OpenRouter | $0.02/1M | From$1/1M | $0.015/1M | 1.05M |
 SiliconFlow | $0.278/1M | $1.11/1M | — | — |
 Alibaba | $0.283/1M | $1.13/1M | — | — |
 CrossModel | $0.30/1M | $1.20/1M | $0.006/1M | — |
 Ofox | $0.30/1M | $1.20/1M | $0.006/1M | 1M |
 Novita AI | $0.30/1M | $1.20/1M | $0.006/1M | — |
 Venice AI | $0.30/1M | $1.20/1M | $0.007/1M | — |
| OpenCode | $0.30/1M | From$1.20/1M | $0.006/1M | — |
 Azure | $0.30/1M | From$1.20/1M | $0.006/1M | — |
 Prime Inference | $0.30/1M | $1.20/1M | $0.006/1M | — |
 EmpirioLabs AI | $0.30/1M | $1.20/1M | $0.30/1M | 1M |
 APIYI | $0.30/1M | From$1.20/1M | — | — |
| Atlas Cloud | $0.30/1M | $1.20/1M | $0.03/1M | — |
 Alibaba | $0.30/1M | From$1.20/1M | — | — |
 NEAR AI Cloud | $0.30/1M | $1.20/1M | $0.006/1M | 1.05M |
 Jiekou.AI | $0.30/1M | $1.20/1M | $0.006/1M | — |
 Impossibl | $0.30/1M | $1.20/1M | $0.006/1M | — |
 Charm Hyper | $0.33/1M | $1.31/1M | $0.03/1M | — |
 TensorX | $0.50/1M | $1.50/1M | $0.13/1M | — |
| AI/ML API | $0.39/1M | $1.56/1M | $0.008/1M | — |
| Baseten | $0.60/1M | $2.40/1M | $0.014/1M | — |
- UnoRouter$0.03
- ZenMux$0.30
- Vercel AI GatewayFrom$0.30
- Kenari$0.304
- FastRouter$0.42
- Deep InfraFrom$0.42
- CometAPIFrom$0.48
- AIHubMix$0.563
- CrazyRouter$0.597
- RequestyFrom$0.60
- Hugging FaceFrom$0.60
- DevPass (LLM Gateway)From$0.60
Specs
- Type
- Text
- Maker
- DeepSeek
- Inputs
- Image, Text
- Outputs
- Text
- Context
- 1.05M≈ 1570 pages of text
- Max output
- 384K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling, Vision
- Released
- Sep 10, 2026
- License
- MITcommercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 763B
- Arena score
- 1664WebDev
- Monthly searches
- 138K
Alternatives to DeepSeek V4.1 Flash
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| DeepSeek V4.1 Flashthis model | $0.03/1M | 1.05M | 1664 | 39 |
| GPT OSS 20B | $0.09/1M | 131K | 1287 | 26 |
| Qwen3 8B | $0.06/1M | — | — | 3 |
 GLM OCR | $0.028/1M | 32K | — | 4 |
 Gemma 4 E2B IT | $0.08/1M | — | — | 1 |
| Qwen3-4B | $0.03/1M | — | — | 2 |
| Qwen2-7B-Instruct | $0.08/1M | — | — | 2 |
 Mistral 7B Instruct | $0.059/1M | — | 1023 | 2 |
| Qwen3.5 4B | $0.07/1M | 262K | — | 4 |
More from DeepSeek
DeepSeek V4 FlashDeepSeek$0.17/1MDeepSeek V4 Flash Vision ExpDeepSeek$0.294/1MDeepSeek V4 ProDeepSeek$0.418/1MDeepSeek R1DeepSeek$1.79/1MDeepSeek V3DeepSeek$0.89/1MDeepSeek V4 Flash 0731DeepSeek$0.133/1MDeepSeek R1 Distill Qwen 7BDeepSeek$0.01/1MDeepSeek R1 Distill Qwen 32BDeepSeek$0.20/1MDeepSeek V4.1 Flash FAQ
The lowest price for DeepSeek V4.1 Flash is $0.03 /1M, at UnoRouter.
UnoRouter, at $0.03 /1M. 39 providers serve DeepSeek V4.1 Flash; the table above lists every one with its price.
DeepSeek V4.1 Flash reads up to 1.05M tokens per request and writes up to 384K.
Yes. DeepSeek V4.1 Flash's weights can be downloaded from its maker's Hugging Face page, under the MIT license.
About 763B, as the safetensors metadata of its official Hugging Face repo states.
39 API providers serve DeepSeek V4.1 Flash. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us