Qwen3.8 Max (0902) API pricing
As of October 22, 2026, Qwen3.8 Max (0902) costs $2.00 per million input tokens and $6.00 per million output tokens on Qwen's own API, with cached input at $0.25 per million.
Qwen3.8 Max (0902) benchmarks and specs · Every Qwen model's price
- Input, per million tokens$2.00
- Output, per million tokens$6.00
- Cached input, per million$0.25
- Context window1M tokens
- Max output131K tokens
- Output speed39 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 | $0.0050 | $5.00 | Yes |
| Repository review | 50K input + 3K output tokens | $0.118 | $118.00 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.460 | $460.00 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $1.32 | $1320.00 |
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: $2.00 input, $6.00 output
Cheaper models as good as Qwen3.8 Max (0902)
Models within two points of Qwen3.8 Max (0902) or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Claude Haiku 5.5$0.50 Overall 67.6 against 68.9 · 92% cheaper output
- DeepSeek V4.1 Flash 1017$0.60 Overall 67.6 against 68.9 · 90% cheaper output
- MiMo-V2.6-Pro$0.87 Overall 68.4 against 68.9 · 86% cheaper output
- Gemini 3.8 Flash$3.75 Overall 69.0 against 68.9 · 38% cheaper output
- Gemini 3.6 Flash$3.75 Overall 68.3 against 68.9 · 38% cheaper output
Qwen3.8 Max (0902) pricing questions
- How much does Qwen3.8 Max (0902) cost per million tokens?
- $2.00 per million input tokens and $6.00 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does Qwen3.8 Max (0902) support prompt caching?
- Yes. OpenRouter lists cached input at $0.25 per million tokens, against $2.00 for uncached input.
- Is there a cheaper model as good as Qwen3.8 Max (0902)?
- Claude Haiku 5.5 scores 67.6 on the LLMBenchmark Index, within two points of Qwen3.8 Max (0902) or above it, and costs $0.50 per million output tokens.
- Has the price of Qwen3.8 Max (0902) changed?
- Not since we started recording it daily on October 21, 2026.