Qwen3-VL 235B-A22B pricing.

Prices checked

Qwen3-VL 235B-A22B costs $0.70 in and $2.80 out per million tokens from Alibaba Cloud; the cheapest price is $0.37 at LLM Gateway, checked .

Alibaba Cloud's own price

Alibaba Cloud

$1.22/M tokens

$0.70 in · $2.80 out

39% above the typical price of the 392 text models we track.

Cheapest price

LLM Gateway

$0.37/M tokens

$0.20 in · $0.88 out

70% less than Alibaba Cloud, and the provider says why.

tool callingreads imagesreasoningopen weights131k contextreleased 1 Apr 2025

Every provider selling Qwen3-VL 235B-A22B

  1. 1

    $0.20 in · $0.88 out · 262k context here

    $0.37/M tokens
  2. 2

    DeepInfra

    Runs it themselves

    $0.20 in · $0.88 out · 262k context here

    $0.37/M tokens
  3. 3

    Eden AI

    Regional price

    $0.20 in · $0.88 out · 262k context here

    $0.37/M tokens
  4. 4

    DeepInfra

    Lower precision (fp8)

    $0.20 in · $0.88 out · 262k context here

    $0.37/M tokens
  5. 5

    LLMTR

    Resells

    $0.20 in · $0.88 out · 262k context here

    $0.37/M tokens
  6. 6

    Fireworks AI

    Runs it themselves

    $0.22 in · $0.88 out · 262k context here

    $0.39/M tokens
  7. 7

    $0.21 in · $0.93 out

    $0.39/M tokens
  8. 8

    Alibaba Cloud (China)

    Regional price

    $0.29 in · $1.15 out

    $0.50/M tokens
  9. 9

    GMI Cloud

    Lower precision (fp8)

    $0.30 in · $1.40 out · 262k context here

    $0.57/M tokens
  10. 10

    Jalapeno Cloud

    Runs it themselves

    $0.30 in · $1.50 out · 129k context here

    $0.60/M tokens
  11. 11

    $0.30 in · $1.50 out

    $0.60/M tokens
  12. 12

    Prime Inference

    Runs it themselves

    $0.30 in · $1.50 out · 262k context here

    $0.60/M tokens
  13. 13

    Helicone

    Runs it themselves

    $0.30 in · $1.50 out · 256k context here

    $0.60/M tokens
  14. 14

    Novita

    Runs it themselves

    $0.30 in · $1.50 out

    $0.60/M tokens
  15. 15

    OpenRouter

    Resells

    $0.21 in · $1.90 out · 262k context here

    $0.63/M tokens
  16. 16

    Merge Gateway

    Runs it themselves

    $0.21 in · $1.90 out

    $0.63/M tokens
  17. 17

    $0.21 in · $1.90 out

    $0.63/M tokens
  18. 18

    Venice

    Runs it themselves

    $0.21 in · $1.90 out · 128k context here

    $0.63/M tokens
  19. 19

    Venice

    Lower precision (fp8)

    $0.21 in · $1.90 out · 128k context here

    $0.63/M tokens
  20. 20

    Parasail

    Lower precision (fp8)

    $0.21 in · $1.90 out

    $0.63/M tokens
  21. 21

    $0.21 in · $1.90 out · 262k context here

    $0.63/M tokens
  22. 22

    NanoGPT

    Resells

    $0.30 in · $1.90 out

    $0.70/M tokens
  23. 23

    OrcaRouter

    Runs it themselves

    $0.40 in · $1.60 out

    $0.70/M tokens
  24. 24

    Alibaba Cloud

    Maker's price

    $0.70 in · $2.80 out

    $1.22/M tokens
  25. 25

    Cortecs

    Same as maker

    $0.62 in · $3.13 out · 256k context here

    $1.25/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.59

A month at Alibaba Cloud's own price

$0.17

A month at LLM Gateway, the cheapest

$0.42

What you save

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

How we count

Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below Alibaba Cloud's own is listed as cheapest only when the provider says why.

Resells
The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Runs it themselves
The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
Regional price
A price list for one region, lower than the international one. A region, not a deal.
Lower precision
The open weights, served at a lower precision than the maker's, so not quite the same product.
Credits
Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
Maker's price
What the lab that trained the model charges on its own API. Every other row is measured against it.
Same as maker
Sold by someone else at the price the maker charges.
Costs more
Sold by someone else for more than the maker charges.

Similar models

Models from other labs that do what Qwen3-VL 235B-A22B does, cheapest first. Each percentage is against Qwen3-VL 235B-A22B's cheapest price, $0.37 per M tokens.

Frequently asked

Who sells Qwen3-VL 235B-A22B cheapest?
LLM Gateway, at $0.20 in and $0.88 out per million tokens, checked 31 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Is Qwen3-VL 235B-A22B open weights?
Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen3-VL 235B-A22B, which is why 24 providers sell it and why their prices differ so much.
How much context does Qwen3-VL 235B-A22B hold?
131,072 tokens in one call, which is about 131k, and it can call your own functions.
How does Qwen3-VL 235B-A22B compare with the rest of the market?
At $1.22 per million tokens, Alibaba Cloud's own price is 39% above the typical $0.88 across the 392 text models we track.

More from Alibaba Cloud