| Spec | Qwen3.8 Max | DeepSeek V4 Pro |
|---|---|---|
| Lowest input | $1.65DeepInfra | $1.30DeepInfra |
| Lowest output | $4.951DeepInfra | $2.60DeepInfra |
| Lowest cached input | $0.206DeepInfra | $0.0036Inference.net |
| Context | 256K | 1.05M |
| Max output | 131K | 524K |
| Providers | 1 | 4 |
| Released | September 3, 2026 | April 24, 2026 |
| Weights | Proprietary | Open |
| Lab | Qwen | DeepSeek |
| Model ID | qwen/qwen3.8-max | deepseek/deepseek-v4-pro |
USD per 1M tokens, as of November 5, 2026.
| Provider | Qwen3.8 Max | DeepSeek V4 Pro |
|---|---|---|
| DeepInfra | $1.65 / $4.951 | $1.30 / $2.60 |
| Inference.net | – | $2.10 / $4.20 |
| Novita AI | – | $1.60 / $3.20 |
| StreamLake | – | $1.74 / $3.48 |
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 |
| DeepSeek V4 ProDeepInfra | $3.90 | $78.00 | $780.00 |
On each model's cheapest provider by input plus output list price.
Input: DeepSeek V4 Pro at $1.30 per million input tokens vs $1.65 (Qwen3.8 Max), 27% lower. Output: DeepSeek V4 Pro at $2.60 per million output tokens vs $4.951 (Qwen3.8 Max), 90% lower. Lowest listed prices as of November 5, 2026.
DeepSeek V4 Pro, with 1.05M tokens vs 256K.
1 provider serves both: DeepInfra. Qwen3.8 Max has 1 provider in total and DeepSeek V4 Pro has 4.
Qwen3.8 Max from $0.206 per million cached input tokens (DeepInfra). DeepSeek V4 Pro from $0.0036 (Inference.net).
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 "deepseek/deepseek-v4-pro".
