Qwen3.6 Max Preview
Qwen · released Apr 27, 2026
- 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 2, 2026Qwen3.6 Max Preview is Alibaba's hosted-only flagship with a 262,144-token request limit and measured strength in coding tasks. It is a premium option for teams that need long-context text work and can accept proprietary-only access.
Choose this for premium coding tasks where its measured coding score is its standout result, or for hard-prompt reasoning and long-context text work at over a quarter-million tokens. Skip it if you need downloadable weights, creative writing quality, or a budget tier — every tracked offer sits at the same premium output level.
The case for it
- Strongest measured capability is coding, with an Arena Coding score 27.6 points above its own overall text score.
- Hard-prompt performance is consistent, with an Arena Hard Prompts score from a late-July 2026 evaluation.
- Two Alibaba Cloud offers deliver measured throughput at 53 and 51.5 tokens per second with nearly identical pricing.
The case against it
- Creative writing is its weakest measured category, sitting 23.8 points below its own overall text score and 71.8 points below its coding score.
- Proprietary weights with no disclosed licence; you cannot download or self-host.
- No budget tier exists — every tracked offer is priced at the same premium output level.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)26th of 143 · 1459.9
CodingWriting and fixing code on its own
Arena Coding26th of 143 · 1508
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Qwen3.6 Max Preview 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 Qwen3.6 Max Preview 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 model7 scoresEvery figure we hold, from 7 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 3 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
- $1.03 in / $6.16 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.03 / $6.16 | 262K | not measured | Unknown | Unknown | Unknown |
| Alibaba Cloudfp8 | $1.03 / $6.16 | 262K | 47 tok/s | No | Yesunknown period | Unknown |
| Alibaba Cloud | $1.04 / $6.24 | 262K | 52 tok/s | No | Yesunknown period | Unknown |
Across the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 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 | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 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 cached-input 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
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-qwen3-6-max-preview