| Spec | Qwen3.8 Max | Qwen3.7 Max |
|---|---|---|
| Lowest input | $1.65DeepInfra | $1.25Novita AI |
| Lowest output | $4.951DeepInfra | $3.75Novita AI |
| Lowest cached input | $0.206DeepInfra | $0.25Novita AI |
| Context | 256K | 1M |
| Max output | 131K | 65.5K |
| Providers | 1 | 1 |
| Released | September 3, 2026 | May 21, 2026 |
| Weights | Proprietary | Proprietary |
| Lab | Qwen | Qwen |
| Model ID | qwen/qwen3.8-max | qwen/qwen3.7-max |
USD per 1M tokens, as of November 5, 2026.
| Provider | Qwen3.8 Max | Qwen3.7 Max |
|---|---|---|
| DeepInfra | $1.65 / $4.951 | – |
| Novita AI | – | $1.25 / $3.75 |
Input / output, USD per 1M tokens.
| Model | 1,000 chat replies2K in, 500 out each | 1,000 agent tasks50K in, 5K out each | Monthly batch job500M in, 50M out |
|---|---|---|---|
| Qwen3.8 MaxDeepInfra | $5.78 | $107.26 | $1,072.55 |
| Qwen3.7 MaxNovita AI | $4.38 | $81.25 | $812.50 |
On each model's cheapest provider by input plus output list price.
Input: Qwen3.7 Max at $1.25 per million input tokens vs $1.65 (Qwen3.8 Max), 32% lower. Output: Qwen3.7 Max at $3.75 per million output tokens vs $4.951 (Qwen3.8 Max), 32% lower. Lowest listed prices as of November 5, 2026.
Qwen3.7 Max, with 1M tokens vs 256K.
None right now. Qwen3.8 Max has 1 provider and Qwen3.7 Max has 1, with no overlap.
Qwen3.8 Max from $0.206 per million cached input tokens (DeepInfra). Qwen3.7 Max from $0.25 (Novita AI).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "qwen/qwen3.8-max" to "qwen/qwen3.7-max".
