DeepSeek V3.2 API pricing
As of October 21, 2026, DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens, the median of 12 providers on OpenRouter, with cached input at $0.028 per million.
DeepSeek V3.2 benchmarks and specs · Every DeepSeek model's price
- Input, per million tokens$0.29
- Output, per million tokens$0.88
- Cached input, per million$0.028
- Context window164K tokens
- Max output66K 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 | $0.0007 | $0.730 | Yes |
| Repository review | 50K input + 3K output tokens | $0.017 | $17.14 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.067 | $66.80 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.99 | $990.00 |
Price history
The price of DeepSeek V3.2 here is the median across 12 providers on OpenRouter, so we do not track price changes for it.
Cheaper models as good as DeepSeek V3.2
Models within two points of DeepSeek V3.2 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- gpt-oss-20b$0.15 Overall 38.5 against 37.9 · 83% cheaper output
- Qwen3.5-Flash$0.26 Overall 50.1 against 37.9 · 70% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 37.9 · 68% cheaper output
- DeepSeek V4 Flash 0731$0.28 Overall 55.2 against 37.9 · 68% cheaper output
- Qwen3 30B A3B Instruct 2507$0.30 Overall 41.5 against 37.9 · 66% cheaper output
DeepSeek V3.2 pricing questions
- How much does DeepSeek V3.2 cost per million tokens?
- $0.29 per million input tokens and $0.88 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does DeepSeek V3.2 support prompt caching?
- Yes. OpenRouter lists cached input at $0.028 per million tokens, against $0.29 for uncached input.
- Is there a cheaper model as good as DeepSeek V3.2?
- gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of DeepSeek V3.2 or above it, and costs $0.15 per million output tokens.
- Has the price of DeepSeek V3.2 changed?
- The price of DeepSeek V3.2 here is the median across 12 providers on OpenRouter, so we do not track price changes for it.