Qwen3.5 397B A17B API pricing
As of October 22, 2026, Qwen3.5 397B A17B costs $0.39 per million input tokens and $2.34 per million output tokens on Qwen's own API, with cached input at $0.30 per million.
Qwen3.5 397B A17B benchmarks and specs · Every Qwen model's price
- Input, per million tokens$0.39
- Output, per million tokens$2.34
- Cached input, per million$0.30
- Context window262K tokens
- Max output236K tokens
- Output speed55 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 | $0.0016 | $1.56 | Yes |
| Repository review | 50K input + 3K output tokens | $0.027 | $26.52 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.101 | $101.40 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We have read Qwen's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $0.39 input, $2.34 output
Cheaper models as good as Qwen3.5 397B A17B
Models within two points of Qwen3.5 397B A17B or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 57.1 · 88% cheaper output
- DeepSeek V4 Flash 0731$0.396 Overall 55.2 against 57.1 · 83% cheaper output
- Claude Haiku 5.5$0.50 Overall 67.6 against 57.1 · 79% cheaper output
- GLM 5.3 Flash$0.50 Overall 66.0 against 57.1 · 79% cheaper output
- GPT-6 Luna$0.50 Overall 59.7 against 57.1 · 79% cheaper output
Qwen3.5 397B A17B pricing questions
- How much does Qwen3.5 397B A17B cost per million tokens?
- $0.39 per million input tokens and $2.34 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does Qwen3.5 397B A17B support prompt caching?
- Yes. OpenRouter lists cached input at $0.30 per million tokens, against $0.39 for uncached input.
- Is there a cheaper model as good as Qwen3.5 397B A17B?
- MiMo-V2.6-Flash scores 60.8 on the LLMBenchmark Index, within two points of Qwen3.5 397B A17B or above it, and costs $0.28 per million output tokens.
- Has the price of Qwen3.5 397B A17B changed?
- Not since we started recording it daily on October 21, 2026.