Model tracker / DeepSeek
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a fast open-weight model from DeepSeek, released 10 September 2026. At DeepSeek it costs $0.30 per million input tokens and $1.20 per million output tokens, with a 1M-token context window. 7 providers serve it; the cheapest is Baseten at $0.30 input and $1.20 output.
- Made by
- DeepSeek
- Released
- 2026-09-10
- Status
- Generally available
- Tier
- Fast
- Weights
- Open
- Context window
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Input
- text, image
- API id
deepseek-flash
DeepSeek V4.1 Flash price at 7 providers
US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.
| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| Baseten · deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $1.20 | $0.007 | $0.525 | – | 2026-10-14 |
| DeepSeek · maker | $0.30 | $1.20 | $0.006 | $0.525 | – | 2026-10-14 |
| Fireworks AI · accounts/fireworks/models/deepseek-v4p1-flash | $0.30 | $1.20 | $0.006 | $0.525 | 50% off | 2026-10-14 |
| Modal Labs · deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $1.20 | $0.03 | $0.525 | – | 2026-10-14 |
| Nebius Group N.V. · deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $1.20 | – | $0.525 | – | 2026-10-14 |
| Novita AI · deepseek/deepseek-v4.1-flash | $0.30 | $1.20 | $0.006 | $0.525 | – | 2026-10-14 |
| Together AI · deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $1.20 | $0.006 | $0.525 | – | 2026-10-14 |
- DeepSeek: Peak rate (01:00-04:00 and 06:00-10:00 UTC on weekdays). Off-peak rates, all other hours and weekends, are half.
- Fireworks AI: US-hosted variant: $0.45 / $1.80. Priority tier: $0.375 / $1.50.
- Modal Labs: Modal Shared Endpoint, billed per token from us-west; plan credits can't be used for Shared Endpoint usage.
- Nebius Group N.V.: Nebius Token Factory publishes no cached-input or batch price for this model.
DeepSeek V4.1 Flash benchmarks
| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| LMArena text score | 1474 | Elo-style score from people voting between answers | Independent |
Scores reported by a model's maker aren't independently checked.
Models like DeepSeek V4.1 Flash
Other fast models closest in price, at each maker's own price or the cheapest provider.
| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.30 | $1.20 | 1M | Open |
| Gemini 3.1 Flash-Lite Google | $0.25 | $1.50 | 1M | Closed |
| GLM-5.3 FlashX Z.ai | $0.37 | $1.25 | 1M | Open |
| Step 3.7 Flash StepFun | $0.20 | $1.15 | 256K | Open |
| Muse Glimmer 30B Meta | $0.35 | $1.50 | 131K | Open |
| Qwen3.6 35B A3B Alibaba | $0.375 | $2.25 | 256K | Open |
Compare them all in the model tracker →
DeepSeek V4.1 Flash on dbggr
- Claude Haiku 5.5 launches at $0.10 per million tokens, matching GPT-6 Luna Daily, 2026-10-07
- OpenAI and Anthropic are reviewing tens of thousands of model incidents Daily, 2026-09-26
DeepSeek V4.1 Flash FAQ
How much does DeepSeek V4.1 Flash cost?
DeepSeek V4.1 Flash costs $0.30 per million input tokens and $1.20 per million output tokens at DeepSeek, and $0.006 per million cached input tokens. Prices are list prices in US dollars, last checked 14 October 2026.
What is DeepSeek V4.1 Flash's context window?
DeepSeek V4.1 Flash takes up to 1,000,000 tokens in one request and writes up to 384,000 tokens in one response.
Is DeepSeek V4.1 Flash open weight?
Yes. DeepSeek publishes the weights, so you can run DeepSeek V4.1 Flash yourself or at any host that serves it.
Where can I use DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is available from Baseten, DeepSeek, Fireworks AI, Modal Labs, Nebius Group N.V., Novita AI and Together AI. At DeepSeek, call it as deepseek-flash.