DeepSeek V3.2 Exp API pricing
As of October 21, 2026, DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens through OpenRouter.
DeepSeek V3.2 Exp benchmarks and specs · Every DeepSeek model's price
- Input, per million tokens$0.27
- Output, per million tokens$0.41
- Cached input, per millionNo cache price listed
- Context window164K tokens
- Max output147K tokens
- Output speedNot measured
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 | $0.0005 | $0.475 | Yes |
| Repository review | 50K input + 3K output tokens | $0.015 | $14.73 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.058 | $58.10 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We read this price every day and have since October 15, 2026. It has not changed yet; any change will be listed here with its date.
- October 15, 2026 First recorded: $0.27 input, $0.41 output
Cheaper models as good as DeepSeek V3.2 Exp
Models within two points of DeepSeek V3.2 Exp or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.
- Ling 3.0 Flash$0.063 Overall 20.1 against 16.6 · 85% cheaper output
- Ling 3.0 Flash VL$0.18 Overall 24.6 against 16.6 · 56% cheaper output
- DeepSeek V4 Flash 0423$0.182 Overall 24.4 against 16.6 · 56% cheaper output
- Solar Mini 4$0.20 Overall 24.1 against 16.6 · 51% cheaper output
- Ling 3.1 Flash$0.225 Overall 41.1 against 16.6 · 45% cheaper output
DeepSeek V3.2 Exp pricing questions
- How much does DeepSeek V3.2 Exp cost per million tokens?
- $0.27 per million input tokens and $0.41 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does DeepSeek V3.2 Exp support prompt caching?
- OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.
- Is there a cheaper model as good as DeepSeek V3.2 Exp?
- Ling 3.0 Flash scores 20.1 on the Artificial Analysis Intelligence Index, within two points of DeepSeek V3.2 Exp or above it, and costs $0.063 per million output tokens.
- Has the price of DeepSeek V3.2 Exp changed?
- Not since we started recording it daily on October 15, 2026.