Qwen3.7 Max
Qwen · released May 21, 2026
- Type
- Closed
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we have no record of published weights
Our take
Written Sep 2, 2026Qwen 3.7 Max is a hosted-only text model from Alibaba that can handle up to one million tokens in a single request. It scores strongly on mathematics and reasoning tests, though its agentic and creative writing scores lag behind its own general performance.
Pick this for long-document work at one million tokens, or for mathematics and reasoning tasks where its measured scores are high. Use it for general chat and coding via its Arena scores, and shop between providers to avoid paying double. Skip it if you need open weights, multimodal input, or strong agentic behaviour — its agent scores are negative across most dimensions.
The case for it
- One-million-token request limit, among the longest we track for hosted models.
- LiveBench Mathematics at 85.25% and Reasoning at 83.34%, strong on refreshed competition problems.
- Competitive coding scores: 74.22% on LiveBench and 1524.84 on Arena Coding.
- Provider prices vary widely for the same model, so shopping around matters.
The case against it
- Agentic coding is far below standard coding: 43.59% versus 74.22% on LiveBench.
- Arena agent scores are negative on task outcome, steerability and instruction-following.
- Proprietary weights with no open licence disclosed.
How good is it?
A closed text model for everyday questions, drafting and coding, with no measured weak spots on the board.
- answering everyday questionsArena Text (overall) · 24th of 168
- drafting and editing proseArena Creative Writing · 36th of 168
- writing and completing codeArena Coding · 18th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)24th of 168 · 1475
CodingWriting and fixing code on its own
Arena Coding18th of 168 · 1525
AgenticPlanning, calling tools, staying on task
Arena Agent40th of 55 · −0.044
WritingDrafting and rewriting prose
Arena Creative Writing36th of 168 · 1441
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $1.25 in / $3.75 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Novita AIDirect | $1.25 / $3.75checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| OpenRouterOpenRouter's own listing | $1.48 / $4.42checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Alibaba CloudThrough OpenRouter | $1.48 / $4.42checked 4 hours ago | 1M131K max reply | 64 tok/s | No | Yesunknown period | Unknown |
| DeepInfraDirect | $2.50 / $7.50checked 4 hours ago | 256K | not measured | Unknown | Unknown | Unknown |
OpenRouter
DeepInfraAcross the 4 listings we hold: 1 says it does 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.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Novita AIDirect | |||
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Alibaba CloudThrough OpenRouter | ✓ | ✓ | ✓ |
| DeepInfraDirect |
Tool calling: 2 of 4 listings say yes, 2 publish no parameter list. JSON output: 2 of 4 listings say yes, 2 publish no parameter list. Strict schema: 2 of 4 listings say yes, 2 publish no parameter list.
Models people weigh against Qwen3.7 Max
When we formed this view
Recent changes
Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- 2 of 4 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 4 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.
- We hold no batch or off-peak rate for any of its listings.
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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- qwen-qwen3-7-max