DeepSeek V4.1 Flash
DeepSeekOfficial DeepSeek V4 API pricing for 2026. DeepSeek V4.1 Flash peak pricing: $0.3/M cache-miss input, $0.006/M cached input, $1.20/M output. Off-peak rates are 50% lower. 1M context, 384K max output.
Input Price
$0.3
cache miss / 1M tokens · Peak
Cached Input
$0.006
per 1M tokens · Peak
Output Price
$1.20
per 1M tokens · Peak
Context Window
1.0M
tokens
Off-peak: $0.15/M cache-miss input, $0.003/M cached input, $0.6/M output. All hours except 01:00-04:00 and 06:00-10:00 UTC on weekdays; Chinese public holidays are off-peak.
DeepSeek V4 API Pricing 2026
New pricing took effect on August 16 at 16:00 UTC. The table shows off-peak to peak ranges per 1M tokens; peak hours are 01:00-04:00 and 06:00-10:00 UTC.
| Model | Cached input / 1M | Cache-miss input / 1M | Output / 1M | Best use |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.003-$0.006 | $0.15-$0.3 | $0.6-$1.20 | High-volume agent traffic |
| DeepSeek V4 Pro | $0.022-$0.044 | $0.66-$1.32 | $1.98-$3.96 | Harder coding and reasoning |
DeepSeek V4 API pricing: use cache-miss input for new prompt tokens and cached input for repeated prefixes.
DeepSeek V4 price: both models support OpenAI-compatible and Anthropic-compatible endpoints.
DeepSeek V4 cost: agent workloads can be far cheaper when repository context and system prompts hit cache.
DeepSeek V4.1 Flash official China pricing (CNY)
Mainland China list price from DeepSeek, in CNY per 1M tokens. Verified 2026-10-25. The USD prices above are DeepSeek's international list price, not a currency conversion.
| Rate | Cached input | Input | Output |
|---|---|---|---|
| Peak | ¥0.04 | ¥2 | ¥8 |
| Off-peak | ¥0.02 | ¥1 | ¥4 |
DeepSeek V4.1 Flash price history
Per 1M cache-miss input / output tokens. See all AI API price changes
- 2026-09-10Price cut$0.44 / $1.32 → $0.3 / $1.20 (-32% / -9%)
Peak rates shown. Off-peak fell from $0.22/$0.66 to $0.15/$0.60. V4.1 Flash also added vision input. DeepSeek pricing
- 2026-08-17Price increase$0.14 / $0.28 → $0.44 / $1.32 (+214% / +371%)
Peak rates shown. DeepSeek introduced time-of-day pricing: off-peak is half the peak rate ($0.22/$0.66). DeepSeek pricing
Cheaper ways to use DeepSeek V4.1 Flash
Current free credits and discounts that apply to DeepSeek models.
- 🐋DeepSeek APIDiscount— Half price outside peak hours: peak is 09:00–12:00 and 14:00–18:00 Beijing time on weekdays; nights, weekends and holidays are 50% off
- 🌋火山方舟（豆包）Free Tier— Up to 5M free inference tokens per day for developers (check the console for the exact allowance)
- 💧硅基流动 SiliconFlowFree Credits— ¥16 voucher after real-name verification; referrer and new user each get ¥16; several small models are freeends 2026-12-31
Specifications
| Provider | DeepSeek |
| Model ID | deepseek-flash |
| Input Price | $0.3 / 1M cache-miss tokens |
| Cached Input Price | $0.006 / 1M tokens |
| Output Price | $1.20 / 1M tokens · Peak |
| Off-peak | $0.15 / 1M cache-miss input, $0.003 / 1M cached input, $0.6 / 1M output · All hours except 01:00-04:00 and 06:00-10:00 UTC on weekdays; Chinese public holidays are off-peak. |
| Context Window | 1.0M tokens |
| Max Output | 384K tokens |
| Capabilities | textvisionfunction_callingstructured_output |
| Release Date | 2026-09-10 |
| Pricing Source | Official DeepSeek pricing |
| Price Verified | 2026-10-25 · DeepSeek V4.1 Flash replaced V4 Flash on 2026-09-10 with lower peak/off-peak pricing. Canonical prices use the conservative peak rate. DeepSeek-V4.1-Flash-1017 (2026-10-17) kept the same prices. Search/Fetch API per-request billing starts 2026-11-01. |
| Notes | Current DeepSeek Flash endpoint (DeepSeek-V4.1-Flash-1017, updated 2026-10-17 at unchanged prices) with native vision. Retired deepseek-v4-flash aliases temporarily route here. Peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays; all other hours are 50% lower. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower. The main column uses peak rates. The last column uses off-peak rates.
| Daily Tokens | Monthly Cost | Annual Cost | Monthly at Off-peak |
|---|---|---|---|
| 10K | $0.225 | $2.70 | $0.1125 |
| 50K | $1.13 | $13.50 | $0.5625 |
| 100K | $2.25 | $27.00 | $1.13 |
| 500K | $11.25 | $135.00 | $5.63 |
| 1.0M | $22.50 | $270.00 | $11.25 |
About DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a large language model by DeepSeek. It features a 1.0M token context window with up to 384K tokens of output per request. The model supports 4 capabilities: text, vision, function_calling, structured_output.
At $0.3 per million cache-miss input tokens and $1.20 per million output tokens, DeepSeek V4.1 Flash is positioned as a cost-effective option in the DeepSeek lineup. Repeated prefix input can be charged at $0.006 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
DeepSeek V4.1 Flash Key Details
- Pricing: $0.3/M cache-miss input tokens, $0.006/M cached input tokens, $1.20/M output tokens
- Context window: 1.0M tokens — one of the largest available
- Max output: 384K tokens per response
- Capabilities: text, vision, function_calling, structured_output
- Highlights: Current DeepSeek Flash endpoint (DeepSeek-V4.1-Flash-1017, updated 2026-10-17 at unchanged prices) with native vision. Retired deepseek-v4-flash aliases temporarily route here. Peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays; all other hours are 50% lower.
- Released: 2026-09-10
Other DeepSeek Models
Similar Price Range
Related Tools
FAQ
How much does DeepSeek V4.1 Flash cost?
DeepSeek V4.1 Flash costs $0.3 per million cache-miss input tokens and $1.20 per million output tokens. Cached input costs $0.006 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $2.70/month before cache-hit savings at peak rates, or $1.35/month at off-peak rates.
What is DeepSeek V4.1 Flash's context window?
DeepSeek V4.1 Flash supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. The maximum output per response is 384K tokens.
Is DeepSeek V4.1 Flash good for my use case?
DeepSeek V4.1 Flash supports text, vision, function_calling, structured_output. As a budget-friendly model, it works well for high-volume tasks like classification, summarization, and simple generation. Use our Pricing Calculator to compare with alternatives.
Is this the official DeepSeek V4 API pricing?
The table above is based on DeepSeek's official model pricing page, last checked against the current public docs. DeepSeek says product prices may change, so verify the official pricing page before committing large production spend.
Should I use DeepSeek V4.1 Flash or DeepSeek V4 Pro?
Use DeepSeek V4.1 Flash for high-volume chat, extraction, coding-agent subtasks, vision input, and cache-heavy repository work. Use DeepSeek V4 Pro for harder text-only coding, reasoning-heavy agent tasks, and stronger long-horizon evaluations.
Does DeepSeek V4 have a free tier?
DeepSeek's public API docs describe billing from topped-up balance or granted balance, but they do not publish a permanent free tier table. Check your platform balance and the official docs for current granted credits before assuming free production usage.