Pricing · DeepSeek
DeepSeek V4.1 Flash
DeepSeek's deepseek-flash, 1M tokens of context. Every number on this page was read off DeepSeek's own pricing
page — never estimated, never recalled from memory.
Pricing
Prices in US dollars per 1M tokens, as DeepSeek's official pricing page printed them when they were last verified, on November 16, 2026.
| Input | $0.30 | per 1M tokens |
|---|---|---|
| Output | $1.20 | per 1M tokens |
| Cached input | $0.006 | per 1M tokens · 0.02× the input price |
| Off-peak input | $0.15 | per 1M tokens · outside Monday to Friday 01:00-04:00 and 06:00-10:00 UTC |
| Off-peak output | $0.60 | per 1M tokens · cached input $0.003 |
The headline prices are DeepSeek's peak rate, which applies only Monday to Friday 01:00-04:00 and 06:00-10:00 UTC: 35 of the 168 hours in a week (21%). The rest of the time every rate is the off-peak one above. Source: the same pricing page, checked September 14, 2026.
At the calculator's starting volume, 1M input tokens and 200K output tokens with no cache hits, DeepSeek V4.1 Flash costs $0.54: $0.30 for input and $0.24 for output, at the peak prices above. Same formula as the calculator; change the volume there.
Where this price sits
$0.30 per 1M input tokens is the 16th cheapest input price of the 82 current models with a verified price on AI Signal, and the 1st of DeepSeek's 2. Output costs 4.0× the input price.
Mentioned in
4 posts on AI Signal cite DeepSeek V4.1 Flash. The sentence is the post's own, taken from where it links here.
-
DeepSeek V4.1 Flash-1017: Same Price, Half Off-Peak · October 19, 2026
The DeepSeek V4.1 Flash page and the DeepSeek V4 Pro page carry the figures above with the date they were read and a link to DeepSeek's page.
-
OpenAI Shuts Down GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, o1, o1-pro and o3-mini on October 23, 2026: the Replacements and What They Cost · October 5, 2026
| Model | Context | Monthly cost | Condition | Verified | |---|---|---|---|---| | Qwen3.7-Flash | 1,000,000 | $0.56 | Singapore price; $1.80 with prompts over 32,000 tokens, $3.60 over 256,000 | September 17, 2026 | | Gemini 2.5 Flash-Lite | 1,048,576 | $1.80 | none | October 5, 2026 | | Qwen3.8-Flash | 1,000,000 | $2.44 | Singapore price | September 11, 2026 | | Qwen3.8-Omni-Flash | 1,000,000 | $2.44 | Singapore price | September 28, 2026 | | DeepSeek V4.1 Flash | 1,000,000 | $5.40 | peak price; $2.70 off-peak | October 5, 2026 |
-
Prompt Caching Is Not 10% Everywhere: What a Cache Hit Costs Across Eight Providers · September 16, 2026
DeepSeek V4 Pro charges $0.044 per million cached tokens on $1.32 of input, and DeepSeek V4.1 Flash $0.006 on $0.30.
-
Five Things Decide What You Pay for a Model, and Only One of Them Is the Model · September 15, 2026
The same clock applies to DeepSeek V4.1 Flash: $0.30 and $1.20 at peak, $0.15 and $0.60 off-peak.
Succession
DeepSeek names DeepSeek V4.1 Flash as the replacement for:
- DeepSeek V4 Flash Vision (experimental) retired shut down September 10, 2026
- DeepSeek V4 Flash retired shut down September 10, 2026
Specifications
DeepSeek V4.1 Flash's API identifier, provider and limits, from the same row of the dataset as the prices above.
| API model id | deepseek-flash | |
|---|---|---|
| Provider | DeepSeek | |
| Context window | 1M tokens | |
| Max output | 384K tokens | |
| Released | September 10, 2026 | |
| Status | Current | |
| Aliases | DeepSeek-V4.1-Flash-1017 | |
DeepSeek V4.1 Flash was released on September 10, 2026. It returns up to 384K tokens per response, against a context window of 1M tokens.
Questions about DeepSeek V4.1 Flash pricing
- How much does DeepSeek V4.1 Flash cost per million tokens?
- $0.30 per 1M input tokens and $1.20 per 1M output tokens, read on DeepSeek's official pricing page on November 16, 2026.
- What does a cached input token cost on DeepSeek V4.1 Flash?
- $0.006 per 1M cached input tokens, 2% of the $0.30 input price.
Released September 10, 2026 with native vision; it replaced DeepSeek V4 Flash and V4 Flash Vision, whose old model names are still accepted and routed to this model at this price. Upgraded on October 17, 2026 under the same API name: DeepSeek's change log (api-docs.deepseek.com/updates/, 'Date: 2026-10-17'), read on 2026-10-19: 'DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model.' The pricing page, the same day: 'MODEL VERSION | DeepSeek-V4.1-Flash-1017 | DeepSeek-V4-Pro-0813 |' and '(1) Use deepseek-flash as the model name. The legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp are still accepted, but the corresponding models have been retired, their requests are served by the DeepSeek-V4.1-Flash-1017 model and billed at the Flash price.' The same page, about the Search and Fetch APIs (billed per request, not per token, so not a promotion on this row's price): 'Note: when you use the DeepSeek API through DeepSeek Harness, Claude Code, or Codex, server-side tool calls already hit the Search and Fetch APIs. These calls are currently free of charge; per-request billing starts at 00:00 Beijing time on November 1, 2026.'
Verified November 16, 2026 against DeepSeek's official pricing page. Confidence: confirmed. No price change recorded for this model. How the data is checked.
Other DeepSeek models with a verified price
- DeepSeek V4 Pro $1.32 in · $3.96 out
Cheaper or equally priced alternatives
Current models with an input price at or below $0.30 per 1M tokens.
- Gemini 3.5 Flash-Lite Google $0.30 in · $2.50 out
- Codestral Mistral $0.30 in · $0.90 out
- DeepSeek V4.1 Flash 1017 Mistral $0.30 in · $1.20 out
- GPT-5.6 Luna OpenAI $0.20 in · $1.20 out
Compare every model in one table →
Work out what this costs at your volume →