Magistral Medium (latest) vs Qwen3.6 Max Preview.
model vs model · prices as of
Qwen3.6 Max Preview takes 3 of 5 rounds against Magistral Medium (latest). It is also the cheaper of the two to run, at $7.61 per million tokens against $12.
Magistral Medium (latest)
$12/M tokens
cheapest we can explain, at Eden AI · $1.35 per 1,000 pages
128k context · tool calling · open weights
Qwen3.6 Max Preview
$7.61/M tokens
cheapest we can explain, at Eden AI · $0.811 per 1,000 pages
262k context · tool calling
List price in (lower wins)
$2/M
$1.30/M
List price out (lower wins)
$5/M
$7.80/M
Cheapest we can explain (lower wins)
$12/M at Eden AI
$7.61/M at Eden AI
Standard price (lower wins)
$11/M
$11.70/M
Cost per 1,000 pages (lower wins)
$1.35
$0.811
Context
128k tokens
262k tokens
Open weights
yes
no
Tool calling
yes
yes
Structured output
not stated
not stated
Reads images
no
no
Reasoning
yes
yes
Released
17 Mar 2025
20 Apr 2026
Providers selling it
5
15
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 3
Eden AI$12 / $7.61
Pioneer$11 / $11.70
Merge Gateway$11 / $11.81
Magistral Medium (latest) then Qwen3.6 Max Preview, per million tokens
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- Qwen3.6 Max Preview
Nous Portal$0.82 / $4.93 $1.03 / $6.1625% dearer ·
Frequently asked
- Which is cheaper, Magistral Medium (latest) or Qwen3.6 Max Preview?
- Qwen3.6 Max Preview, at $7.61 per million tokens against $12 for Magistral Medium (latest), three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- Magistral Medium (latest): $12 at Eden AI. Qwen3.6 Max Preview: $7.61 at Eden AI.
- Can I buy both from one provider?
- Yes. 3 providers sell both: Eden AI, Pioneer, Merge Gateway. The cheapest of them for the two together is Eden AI.
- Which holds more context?
- Qwen3.6 Max Preview, at 262k tokens against 128k.
Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.