Qwen3-Max pricing
Qwen3-Max, Mid-tier from DeepInfra, costs $1.20 per 1M input tokens and $6.00 per 1M output tokens.
Input$1.20per 1M tokens
Output$6.00per 1M tokens
Context window250Ktokens
TierMidDeepInfra
Price your own workload against Qwen3-Max in the calculator →
Specs and pricing
| Provider | DeepInfra |
| Tier | Mid |
| Context window | 250K tokens |
| Max output | — |
| Input price | $1.20 / 1M tokens |
| Output price | $6.00 / 1M tokens |
| Cache read | $0.24 / 1M tokens |
| Modalities | text |
Note. Context listed on page as '250k'.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $1.20 | $1.50 | $2.70 |
| 10,000,000 in / 2,500,000 out | $12.00 | $15.00 | $27.00 |
| 100,000,000 in / 25,000,000 out | $120.00 | $150.00 | $270.00 |
Cheaper alternatives
Same tier (Mid), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| GPT-OSS 120B | OpenRouter | $0.037 | $0.17 | 97.1% cheaper blended |
| GPT-OSS 120B | Novita AI | $0.05 | $0.25 | 95.8% cheaper blended |
| Nemotron 3 Super | OpenRouter | $0.085 | $0.40 | 93.1% cheaper blended |
| DeepSeek V4 Flash 0731 | Baseten | $0.13 | $0.26 | 92.8% cheaper blended |
| GPT OSS 120B | Baseten | $0.10 | $0.50 | 91.7% cheaper blended |