KuraberuAIupdated 16 Sept 2026

Qwen3.5 35B-A3B pricing.

prices as of · 27 providers · 31 prices

Alibaba Cloud's Qwen3.5 35B-A3B holds 262k 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.

Qwen3.5 35B-A3B costs $0.25 in and $2 out per million tokens from Alibaba Cloud; the cheapest price we can explain is $0.63 at OrcaRouter, checked 16 Sept 2026.

tool callingreads imagesreasoningstructured outputopen weights262k contextreleased 23 Feb 2026
Compare withvs GPT-5.1-Codex-Minivs GPT-5 Minivs Seed 1.6or any model →

Alibaba Cloud list price

$2.75/M tokens

$0.25 in · $2 out

read · 23% below the market median

Cheapest price we can explain

$0.63/M tokens

$0.06 in · $0.46 out · 77% under list

OrcaRouter

read

What it costs for your work

pages a month

Alibaba Cloud list price

$0.27a month

cheapest we can explain · OrcaRouter

$0.0617a month

difference

$0.208saved

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 Qwen3.5 35B-A3B

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.

    Alibaba Cloud ↗

    $0.25 / $2in / out per M

    1.00×of list price

Cheaper, and we know why

21 prices

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

  • OrcaRouter

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

    $0.06 / $0.46in / out per M

    0.23×of list price

  • Empirio Labs

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

    256k context hereEmpirio Labs ↗

    $0.06 / $0.46in / out per M

    0.23×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.

    256k context here

    $0.06 / $0.46in / out per M

    0.23×of list price

  • 302.AI

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

    $0.06 / $0.46in / out per M

    0.23×of list price

  • Darkbloom

    Serves the open weights at fp4, a lower precision than the maker's, so not quite the same product.

    fp4 precision

    $0.08 / $0.75in / out per M

    0.36×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.

    Nous Portal ↗

    $0.08 / $0.75in / out per M

    0.36×of list price

  • Requesty

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

    Requesty ↗

    $0.14 / $1in / out per M

    0.52×of list price

  • DeepInfra

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

    DeepInfra ↗

    $0.14 / $1in / out per M

    0.52×of list price

  • DeepInfra

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

    fp8 precisionDeepInfra ↗

    $0.14 / $1in / out per M

    0.52×of list price

  • Eden AI

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

    Eden AI ↗

    $0.14 / $1in / 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 ↗

    $0.15 / $1in / out per M

    0.53×of list price

  • TrustedRouter

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

    TrustedRouter ↗

    $0.15 / $1.06in / out per M

    0.54×of list price

  • OpenRouter

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

    OpenRouter ↗

    $0.16 / $1.30in / out per M

    0.65×of list price

  • Kilo Gateway

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

    Kilo Gateway ↗

    $0.16 / $1.30in / out per M

    0.65×of list price

  • NanoGPT

    10% under the list price, an ordinary reseller margin.

    260k context hereNanoGPT ↗

    $0.23 / $1.80in / out per M

    0.90×of list price

  • NanoGPT

    10% under the list price, an ordinary reseller margin.

    260k context hereNanoGPT ↗

    $0.23 / $1.80in / out per M

    0.90×of list price

  • Atlas Cloud

    10% under the list price, an ordinary reseller margin.

    fp8 precisionAtlas Cloud ↗

    $0.23 / $1.80in / out per M

    0.90×of list price

  • Atlas Cloud

    10% under the list price, an ordinary reseller margin.

    Atlas Cloud ↗

    $0.23 / $1.80in / out per M

    0.90×of list price

  • SiliconFlow

    4% under the list price, an ordinary reseller margin.

    SiliconFlow ↗

    $0.24 / $1.80in / out per M

    0.92×of list price

  • SiliconFlow

    4% under the list price, an ordinary reseller margin.

    fp8 precisionSiliconFlow ↗

    $0.24 / $1.80in / out per M

    0.92×of list price

  • SiliconFlow (China)

    8% under the list price, an ordinary reseller margin.

    SiliconFlow (China) ↗

    $0.23 / $1.86in / out per M

    0.93×of list price

Same price as the maker

9 prices

The same price the maker charges, sold by someone else.

  • Weights & Biases

    The same price Alibaba Cloud charges.

    $0.25 / $1.25in / out per M

    0.73×of list price

  • Mixlayer

    The same price Alibaba Cloud charges.

    $0.25 / $1.30in / out per M

    0.75×of list price

  • Venice

    25% above Alibaba Cloud's price.

    256k context hereVenice ↗

    $0.31 / $1.25in / out per M

    0.80×of list price

  • Ofox

    16% above Alibaba Cloud's price.

    256k context hereOfox ↗

    $0.29 / $1.83in / out per M

    0.98×of list price

  • Novita

    The same price Alibaba Cloud charges.

    Novita ↗

    $0.25 / $2in / out per M

    1.00×of list price

  • Hugging Face Inference Providers

    The same price Alibaba Cloud charges.

    Hugging Face Inference Providers ↗

    $0.25 / $2in / out per M

    1.00×of list price

  • Jalapeno Cloud

    The same price Alibaba Cloud charges.

    $0.25 / $2in / out per M

    1.00×of list price

  • Jiekou

    The same price Alibaba Cloud charges.

    Jiekou ↗

    $0.25 / $2in / out per M

    1.00×of list price

  • LLMTR

    The same price Alibaba Cloud charges.

    256k context hereLLMTR ↗

    $0.25 / $2in / out per M

    1.00×of list price

Frequently asked

Who sells Qwen3.5 35B-A3B cheapest?
OrcaRouter, at $0.06 in and $0.46 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
Is Qwen3.5 35B-A3B open weights?
Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen3.5 35B-A3B, which is why 27 providers sell it and why their prices differ so much.
How much context does Qwen3.5 35B-A3B hold?
262,144 tokens in one call, which is about 262k, and it can call your own functions.
How does Qwen3.5 35B-A3B compare with the rest of the market?
At $2.75 per million tokens, Alibaba Cloud's price is 23% below 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 contextKimi K2.6Kimi K2.7 CodeGLM-5.1Kimi K2.5