DeepSeek V4 Flash Thinking pricing
Source: litellm · updated 2026-10-28
Short answer: DeepSeek V4 Flash Thinking costs $0.250 per million input tokens and $1.75 per million output tokens. That is a 3:1 blended rate of $0.625 per million tokens, ranking it #285 of 713 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.250 |
| Output, per 1M tokens | $1.75 |
| Output รท input multiple | 7.00× |
| 3:1 blended, per 1M tokens | $0.625 |
| Context window | 200,000 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.250 | $0.438 | $0.688 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $2.50 | $4.38 | $6.88 | ||||
| 100M in / 25M out | $25.00 | $43.75 | $68.75 |
Other libertai models
| Model | Input | Output |
|---|---|---|
| Hermes 3.8 B Tee | $0.150 | $0.600 |
| Gemma 4 31 B It Thinking | $0.150 | $0.400 |
| Qwen 3.6 27 B Thinking | $0.150 | $0.500 |
| Qwen 3.6 35 B A3 B Thinking | $0.150 | $0.500 |
| Qwen 3.5 122 B A10 B Thinking | $0.250 | $1.75 |
Compare against
Cheaper alternatives
Next cheaper option: Skyfall 36 B at $0.550 per 1M input tokens. Next step up: Qwen 3 VL 235 B A22 B Instruct at $0.210 per 1M input tokens.