DeepSeek V4.1 Flash API pricing
As of October 21, 2026, DeepSeek V4.1 Flash costs $0.049 per million input tokens and $0.525 per million output tokens through OpenRouter, with cached input at $0.001 per million.
DeepSeek V4.1 Flash benchmarks and specs · Every DeepSeek model's price
- Input, per million tokens$0.049
- Output, per million tokens$0.525
- Cached input, per million$0.001
- Context window1.05M tokens
- Max output944K tokens
- Output speed223 tok/s
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0003 | $0.311 | Yes |
| Repository review | 50K input + 3K output tokens | $0.0040 | $4.03 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.015 | $15.05 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We have recorded 6 price changes since we started reading the price daily on October 15, 2026.
- October 15, 2026 First recorded: $0.0238 input, $0.72 output
- October 16, 2026 $0.72 to $0.684 output, $0.0238 to $0.018 input
- October 17, 2026 $0.684 to $0.70 output, $0.018 to $0.04 input
- October 18, 2026 $0.70 to $0.144 output, $0.04 to $0.0648 input
- October 19, 2026 $0.144 to $0.08 output, $0.0648 to $0.0304 input
- October 20, 2026 $0.08 to $0.0112 output, $0.0304 to $0.0352 input
- October 21, 2026 $0.0112 to $0.525 output, $0.0352 to $0.049 input
Cheaper models as good as DeepSeek V4.1 Flash
Models within two points of DeepSeek V4.1 Flash or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.
- Ling 3.0 Flash VL$0.18 Overall 24.6 against 24.7 · 66% cheaper output
- DeepSeek V4 Flash 0423$0.182 Overall 24.4 against 24.7 · 65% cheaper output
- Solar Mini 4$0.20 Overall 24.1 against 24.7 · 62% cheaper output
- Ling 3.1 Flash$0.225 Overall 41.1 against 24.7 · 57% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 37.9 against 24.7 · 47% cheaper output
DeepSeek V4.1 Flash pricing questions
- How much does DeepSeek V4.1 Flash cost per million tokens?
- $0.049 per million input tokens and $0.525 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does DeepSeek V4.1 Flash support prompt caching?
- Yes. OpenRouter lists cached input at $0.001 per million tokens, against $0.049 for uncached input.
- Is there a cheaper model as good as DeepSeek V4.1 Flash?
- Ling 3.0 Flash VL scores 24.6 on the Artificial Analysis Intelligence Index, within two points of DeepSeek V4.1 Flash or above it, and costs $0.18 per million output tokens.
- Has the price of DeepSeek V4.1 Flash changed?
- Yes, 6 times since October 15, 2026; the dates are listed on this page.