Qwen3-VL 235B-A22B pricing.

prices as of · 24 providers · 27 prices

Alibaba Cloud's Qwen3-VL 235B-A22B holds 131k tokens of context, reads images as well as text and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.

Qwen3-VL 235B-A22B costs $0.70 in and $2.80 out per million tokens from Alibaba Cloud; the cheapest price we can explain is $1.48 at LLM Gateway, checked 16 Sept 2026.

tool callingreads imagesreasoningopen weights131k contextreleased 1 Apr 2025

Alibaba Cloud list price

$4.90/M tokens

$0.70 in · $2.80 out

read · 38% above the market median

Cheapest price we can explain

$1.48/M tokens

$0.20 in · $0.88 out · 70% under list

LLM Gateway
View at LLM Gateway

read

What it costs for your work

pages a month

Alibaba Cloud list price

$0.588a month

cheapest we can explain · LLM Gateway

$0.173a month

difference

$0.415saved

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.

Every provider selling Qwen3-VL 235B-A22B

Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Alibaba Cloud's price.

The maker's list price

1 price

What the lab that trained the model charges on its own API.

  • Alibaba Cloud

    The price Alibaba Cloud charges for the model it trained. Every row below is measured against it.

    $0.70 / $2.80in / out per M

    1.00×of list price

Cheaper, and we know why

26 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • LLM Gateway

    Routes to a host serving the open weights; precision not disclosed.

    $0.20 / $0.88in / out per M

    0.30×of list price

  • DeepInfra

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    262k context hereDeepInfra

    $0.20 / $0.88in / out per M

    0.30×of list price

  • Eden AI

    Alibaba's China-region price list, which is lower than the international one. A region, not a deal.

    $0.20 / $0.88in / out per M

    0.30×of list price

  • DeepInfra

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    262k context herefp8 precisionDeepInfra

    $0.20 / $0.88in / out per M

    0.30×of list price

  • Nous Portal

    Resells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.

    262k context hereNous Portal

    $0.20 / $0.88in / out per M

    0.30×of list price

  • Fireworks AI

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    262k context hereFireworks AI

    $0.22 / $0.88in / out per M

    0.31×of list price

  • TrustedRouter

    Routes to a host serving the open weights; precision not disclosed.

    262k context hereTrustedRouter

    $0.21 / $0.93in / out per M

    0.32×of list price

  • Kilo Gateway

    Routes to a host serving the open weights; precision not disclosed.

    $0.26 / $1.04in / out per M

    0.37×of list price

  • Alibaba Cloud (China)

    Alibaba's China-region Model Studio, which prices the Qwen models below the international list. A region, not a deal.

    $0.29 / $1.15in / out per M

    0.41×of list price

  • Merge Gateway

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.29 / $1.15in / out per M

    0.41×of list price

  • NanoGPT

    Routes to a host serving the open weights; precision not disclosed.

    $0.30 / $1.20in / out per M

    0.43×of list price

  • SiliconFlow (China)

    SiliconFlow's China-region catalog, priced in the domestic market.

    262k context hereSiliconFlow (China)

    $0.30 / $1.50in / out per M

    0.49×of list price

  • Novita

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.30 / $1.50in / out per M

    0.49×of list price

  • Helicone

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    256k context here

    $0.30 / $1.50in / out per M

    0.49×of list price

  • Hugging Face Inference Providers

    Routes to a host serving the open weights; precision not disclosed.

    $0.30 / $1.50in / out per M

    0.49×of list price

  • Jalapeno Cloud

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    129k context here

    $0.30 / $1.50in / out per M

    0.49×of list price

  • SiliconFlow

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    262k context hereSiliconFlow

    $0.30 / $1.50in / out per M

    0.49×of list price

  • Novita

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.

    bf16 precisionNovita

    $0.30 / $1.50in / out per M

    0.49×of list price

  • OpenRouter

    Routes to a host serving the open weights; precision not disclosed.

    262k context hereOpenRouter

    $0.21 / $1.90in / out per M

    0.52×of list price

  • TensorX

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    131k context here

    $0.21 / $1.90in / out per M

    0.52×of list price

  • Venice

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    128k context hereVenice

    $0.21 / $1.90in / out per M

    0.52×of list price

  • Venice

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    128k context herefp8 precisionVenice

    $0.21 / $1.90in / out per M

    0.52×of list price

  • Parasail

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    fp8 precisionParasail

    $0.21 / $1.90in / out per M

    0.52×of list price

  • OrcaRouter

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.40 / $1.60in / out per M

    0.57×of list price

  • Vercel AI Gateway

    Routes to a host serving the open weights; precision not disclosed.

    $0.40 / $1.60in / out per M

    0.57×of list price

showing the 25 cheapest of 26 · every row in the open dataset

Frequently asked

Who sells Qwen3-VL 235B-A22B cheapest?
LLM Gateway, at $0.20 in and $0.88 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
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 $4.90 per million tokens, Alibaba Cloud's price is 38% above the $3.55 median across the 337 text models we track.
More from Alibaba CloudQwen3.8 27BQwen3.5 397B-A17BQwen3.6 35B-A3BQwen3 235B-A22BSimilar contextgpt-oss-120bDeepSeek V3.2Llama-3.3-70B-Instructgpt-oss-20b