DeepSeek V4 Flash 0731: API pricing, providers and specs
DeepSeek V4 Flash 0731 is a text model by DeepSeek. 25 providers serve it, from $0.133 to $1.32 /1M; the lowest price is at OpenRouter.
How DeepSeek V4 Flash 0731 compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.133 /1M, its lowest price undercuts 90% 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.
- 25 providers serve it; 91% of comparable models have fewer.
- Its weights are open under the MIT license: commercial use allowed.
DeepSeek V4 Flash 0731 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 |
|---|---|---|---|---|
| OpenRouter | $0.044/1M | From$0.133/1M | $0.001/1M | 1.05M |
 Requesty | $0.076/1M | From$0.153/1M | $0.014/1M | 1.05M |
| Vercel AI Gateway | $0.076/1M | $0.153/1M | $0.014/1M | 1M |
 Hugging Face | $0.06/1M | From$0.18/1M | — | — |
 Deep Infra | $0.06/1M | From$0.18/1M | $0.015/1M | — |
 Boundless | $0.04/1M | $0.21/1M | $0.02/1M | — |
 Venice AI | $0.13/1M | From$0.26/1M | $0.028/1M | — |
| Baseten | $0.13/1M | $0.26/1M | $0.028/1M | — |
 Impossibl | $0.14/1M | $0.28/1M | $0.028/1M | — |
 AIHubMix | $0.142/1M | From$0.284/1M | $0.028/1M | 1M |
 TensorX | $0.25/1M | $0.30/1M | $0.06/1M | — |
 Cortecs | $0.083/1M | $0.415/1M | $0.06/1M | — |
 CometAPI | $0.12/1M | From$0.48/1M | — | — |
 OrcaRouter | $0.22/1M | $0.66/1M | $0.007/1M | 1.05M |
 EmpirioLabs AI | $0.424/1M | $1.27/1M | $0.424/1M | 1M |
 Alibaba | $0.44/1M | From$1.32/1M | — | — |
 Ofox | $0.44/1M | $1.32/1M | $0.014/1M | 1M |
 Novita AI | $0.44/1M | $1.32/1M | $0.028/1M | — |
 Cloudflare Workers AI | $0.44/1M | $1.32/1M | — | — |
 Charm Hyper | $0.44/1M | $1.32/1M | $0.044/1M | — |
 Prime Inference | $0.44/1M | $1.32/1M | — | — |
 APIYI | $0.44/1M | $1.32/1M | — | — |
| Atlas Cloud | $0.44/1M | $1.32/1M | $0.028/1M | — |
| BytePlus | $0.44/1M | From$1.32/1M | $0.014/1M | — |
 Jiekou.AI | $0.44/1M | $1.32/1M | $0.028/1M | — |
- OpenRouterFrom$0.133
- Vercel AI Gateway$0.153
- RequestyFrom$0.153
- Hugging FaceFrom$0.18
- Deep InfraFrom$0.18
- Boundless$0.21
- Baseten$0.26
- Venice AIFrom$0.26
- Impossibl$0.28
- AIHubMixFrom$0.284
- TensorX$0.30
- Cortecs$0.415
Specs
- Type
- Text
- Maker
- DeepSeek
- Inputs
- Text
- Outputs
- Text
- Context
- 1.05M≈ 1570 pages of text
- Max output
- 384K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling
- Released
- Jul 31, 2026
- License
- MITcommercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 304B
- Monthly searches
- 4K
2 uncensored versions · See them
Alternatives to DeepSeek V4 Flash 0731
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731this model | $0.133/1M | 1.05M | — | 25 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
| Qwen3.8 Flash Next | $0.376/1M | 262K | 1628 | 5 |
 Ling 3.1 Flash | $0.225/1M | 262K | — | 5 |
| Qwen2-1.5B-Instruct | $0.20/1M | — | — | 2 |
| Qwen3.5 Flash | $0.287/1M | 1M | — | 1 |
| GPT OSS 120B | $0.14/1M | 131K | 1366 | 32 |
 MiMo-V2.6-Flash | $0.10/1M | 1.05M | 1634 | 22 |
More from DeepSeek
DeepSeek V4.1 FlashDeepSeek$0.03/1MDeepSeek 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 R1 Distill Qwen 7BDeepSeek$0.01/1MDeepSeek R1 Distill Qwen 32BDeepSeek$0.20/1MDeepSeek V4 Flash 0731 FAQ
The lowest price for DeepSeek V4 Flash 0731 is $0.133 /1M, at OpenRouter.
OpenRouter, at $0.133 /1M. 25 providers serve DeepSeek V4 Flash 0731; the table above lists every one with its price.
DeepSeek V4 Flash 0731 reads up to 1.05M tokens per request and writes up to 384K.
Yes. DeepSeek V4 Flash 0731's weights can be downloaded from its maker's Hugging Face page, under the MIT license.
About 304B, as the safetensors metadata of its official Hugging Face repo states.
25 API providers serve DeepSeek V4 Flash 0731. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us