Qwen / qwen/qwen3-max
Qwen3-Max - access through LLMTR
Qwen3-Max was Qwen's top-tier model for hard agent tasks and deep reasoning, with a 256,000-token context window and tool calling. The provider shut the model down and it was retired on 10 October 2026: requests for this identifier are rejected with `model_retired` (HTTP 410). Use `qwen/qwen3.8-max` instead: it has a 1,000,000-token context window, accepts images and has one rate at every prompt length: $2.00 input, $6.00 output and $0.25 cached input per 1M tokens. This model charged $1.20 / $6.00 up to 32K input, $2.40 / $12.00 up to 128K and $3.00 / $15.00 above; up to 32K input and cached input cost more and output is the same, above it everything costs less. It reasons by default; send `reasoning: false` to turn it off.
This model has been retired
API requests are not allowed; model features and pricing are shown for reference only.
Retired on: 2026-10-10
Suggested alternative: Qwen3.8-Max (qwen/qwen3.8-max)
Technical specifications
| Canonical ID | qwen/qwen3-max |
|---|---|
| Provider | Qwen |
| Context window | 256,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | starting | catalog | $0.240000 |
Example usage
The example below uses the model recommended in its place.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"qwen/qwen3.8-max","messages":[{"role":"user","content":"Hello"}]}'Related models
- Qwen3.8-Max qwen/qwen3.8-max
- Qwen3.7-Max qwen/qwen3.7-max
- Qwen3.7-Plus qwen/qwen3.7-plus
- Qwen3.8-Flash qwen/qwen3.8-flash
- Qwen3.6-Flash qwen/qwen3.6-flash
- Qwen-Plus qwen/qwen-plus
- Qwen-Plus-2025-01-25 qwen/qwen-plus-2025-01-25
- Qwen-Plus-2025-04-28 qwen/qwen-plus-2025-04-28