Qwen3 Max
Qwen · released Sep 23, 2025
- Type
- Proprietary
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we hold no downloadable copy
Our take
Written Aug 3, 2026Qwen 3 Max is a hosted-only text model from Alibaba with a 262,144-token request limit and measured coding strength on the Arena leaderboard. Its five providers span a wide price range, so routing to the cheapest host matters.
Choose this for long-context text work where a proprietary API is acceptable, or for coding workloads where its Arena Coding score is the standout measured skill. Route carefully: the cheapest host undercuts the most expensive by more than double on both input and output. Skip it if you need downloadable weights, creative writing quality, or any image, audio or video input.
The case for it
- Coding is the standout measured skill, scoring 22.6 points above its own overall Text Elo and 86.9 points above its own Creative Writing score.
- Wide price spread across five providers means cost-sensitive routing can cut spend by more than half.
- Arena Text overall score drifted only 0.0731 points between consecutive evaluations, suggesting stable measured performance.
The case against it
- Creative writing is the weakest measured Arena dimension, sitting 39.8 points below its overall Text Elo and 86.9 points below its Coding score.
- No open-weights option for local deployment or fine-tuning; the licence field is undisclosed.
- Throughput is unverified on three of the five tracked offers, with only Alibaba's two listings showing measured speed.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)49th of 143 · 1434.6
CodingWriting and fixing code on its own
Arena Coding49th of 143 · 1481.7
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Qwen3 Max for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Qwen3 Max placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Cheapest of 5 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.78 in / $3.90 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.78 / $3.90 | 262K | not measured | Unknown | Unknown | Unknown |
| Alibaba Cloudfp8 | $0.78 / $3.90 | 262K | 34 tok/s | No | Yesunknown period | Unknown |
| Alibaba Cloud | $0.78 / $3.90 | 262K | 40 tok/s | No | Yesunknown period | Unknown |
| DeepInfra | $1.20 / $6.00 | 256K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $2.11 / $8.45 | 262K | not measured | Unknown | Unknown | Unknown |
DeepInfra
Novita AIAcross the 5 listings we hold: 2 say they do not train on prompts, 0 say they do and 3 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Alibaba Cloudfp8 | ✓ | ✓ | ✓ |
| Alibaba Cloud | ✓ | ✓ | ✓ |
| DeepInfra | |||
| Novita AI |
Tool calling: 3 of 5 listings say yes, 2 publish no parameter list. JSON output: 3 of 5 listings say yes, 2 publish no parameter list. Strict schema: 3 of 5 listings say yes, 2 publish no parameter list.
Models people weigh against Qwen3 Max
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 2 of 5 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 3 of 5 listings do not say whether they train on prompts.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- qwen-qwen3-max