Unofficial page — not affiliated with or endorsed by DeepSeek. Chat answers are AI-generated and may be wrong.
DeepSeek · Available now
DeepSeek 4.1 (2026): only the V4.1 Flash version exists
DeepSeek 4.1 is only available as V4.1 Flash, released on September 10, 2026, priced at $0.30 per million input and $1.20 per million output tokens at peak, with a 1M-token context.
- Maker
- DeepSeek
- Type
- Text
- Released
- 2026-09-10
- OpenRouter id
- deepseek/deepseek-v4.1-flash-1017
Per million tokens
Price
| - | Input | Output | Source |
|---|---|---|---|
| DeepSeek — Peak hours (cache miss) | $0.30 | $1.2 | api-docs.deepseek.com |
| DeepSeek — Off-peak (cache miss) | $0.15 | $0.60 | api-docs.deepseek.com |
| Via OpenRouter (deepseek/deepseek-v4.1-flash-1017) | $0.30 | $1.2 | Together or Fireworks via OpenRouter (the hosts the chat uses; not DeepSeek’s own endpoint) · openrouter.ai |
Checked
Facts, with sources
- DeepSeek released V4.1-Flash on September 10, 2026.Source: api-docs.deepseek.com · checked 2026-11-11
- Only the Flash version of V4.1 exists: DeepSeek has published no V4.1 Pro, and the Pro model on its price page is still deepseek-v4-pro (V4-Pro-0813).Source: api-docs.deepseek.com · checked 2026-11-11
- DeepSeek’s pricing page says the API model deepseek-flash is now served by the V4.1-Flash-1017 snapshot.Source: api-docs.deepseek.com · checked 2026-11-11
- The smallest model of DeepSeek’s new architecture family, with native image understanding; 552B total parameters, about 8B active for input and about 16B active for output.Source: api-docs.deepseek.com · checked 2026-11-11
- Context 1M tokens; maximum output 384K tokens.Source: api-docs.deepseek.com · checked 2026-11-11
- Cache-miss input $0.30 per million tokens at peak and $0.15 off-peak; output $1.20 at peak and $0.60 off-peak. Peak is Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, except Chinese public holidays.Source: api-docs.deepseek.com · checked 2026-11-11
- Listed on OpenRouter as deepseek/deepseek-v4.1-flash-1017 (since October 17, 2026), with text and image input.Source: openrouter.ai · checked 2026-11-11
- The chat on this page reaches the model through OpenRouter on Together or Fireworks only, at $0.30 per million input and $1.20 per million output tokens (their listed price); it does not use DeepSeek’s own API endpoint.Source: openrouter.ai · checked 2026-11-11
Use it now
Chat
FAQ
Questions
Is there a DeepSeek V4.1 Pro?
No. Only V4.1 Flash exists. The Pro model on DeepSeek’s price page is still deepseek-v4-pro (V4-Pro-0813).
When was DeepSeek V4.1 Flash released?
DeepSeek announced V4.1-Flash on September 10, 2026. The API name deepseek-flash is now served by the V4.1-Flash-1017 snapshot.
How much does DeepSeek V4.1 Flash cost?
Cache-miss input is $0.30 per million tokens at peak and $0.15 off-peak; output is $1.20 at peak and $0.60 off-peak.
How big is it?
DeepSeek says 552B total parameters, about 8B active for input and 16B for output, with a 1M-token context and up to 384K output tokens.
Can it read images?
Yes. DeepSeek describes native image understanding, and OpenRouter lists text and image input.
Which host answers in the chat?
Together or Fireworks, reached through OpenRouter, at $0.30 / $1.20 per million tokens. The chat does not use DeepSeek’s own API endpoint.
Is this DeepSeek’s website?
No. This page is unofficial and not affiliated with or endorsed by DeepSeek. Every fact links to its source.