x-ai
Qwen3 Max vs SpaceXAI: Grok 4.3
62.2 overall · $1.56 / 1M
// qwen
Qwen3 Max
qwen/qwen3-max
tool callingprompt caching
Qwen3 Max costs $0.780 per 1M input tokens and $3.90 per 1M output tokens with a 262K-token context window.
A tool-calling model from qwen, released Sep 23, 2025. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.780
- Output / 1M
- $3.90
- Context
- 262K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.780 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $3.90 |
| Blended price 3:1 input:output — #105 most expensive of 343 listed models | $1.56 |
| Cached input read Blank means not priced separately — not free | $0.156 |
| Cache write | $0.975 |
| Context window | 262,144 tokens |
| Max output | 65,536 tokens |
| Input modalities | text |
| Tool calling | Yes |
| Extended reasoning | No |
| Knowledge cutoff | 2025-06-30 |
| Listed | Sep 23, 2025 |
What Qwen3 Max costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $454.27/mo |
| RAG assistant 8K in / 600 out × 100K requests | $608.40/mo |
| Coding agent 40K in / 4K out × 20K requests | $586.56/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,041/mo |
| Bulk classification 500 in / 20 out × 5M requests | $2,028/mo |
Compare Qwen3 Max with
Benchmarked models at a similar price.
Qwen3 Max FAQ
How much does Qwen3 Max cost?
Qwen3 Max lists at $0.780 per 1M input tokens and $3.90 per 1M output tokens, with cached input reads at $0.156 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $608.40 at list price.
What is the context window of Qwen3 Max?
Qwen3 Max accepts up to 262,144 tokens of context and can return up to 65,536 output tokens per response.
Does Qwen3 Max support tool calling?
Yes — Qwen3 Max supports tool (function) calling. It accepts text input.
How does Qwen3 Max score on benchmarks?
LiveBench has not published a run for Qwen3 Max yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Qwen3 Max?
On OpenRouter the model ID is "qwen/qwen3-max". It was listed on Sep 23, 2025.
More from qwen
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.