Qwen3 235B-A22B pricing.

• Alibaba Cloud

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

  Alibaba Cloud ↗

  $0.70 / $2.80in / out per M

  1.00×of list price

• OpenRouter

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

  262k context hereOpenRouter ↗

  $0.09 / $0.35in / out per M

  0.13×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 ↗

  $0.09 / $0.35in / out per M

  0.13×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 ↗

  $0.07 / $0.46in / out per M

  0.14×of list price

• Cortecs

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

  262k context hereCortecs ↗

  $0.07 / $0.47in / out per M

  0.14×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 ↗

  $0.09 / $0.55in / out per M

  0.17×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 ↗

  $0.09 / $0.55in / out per M

  0.17×of list price

• LLM Gateway

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

  262k context hereLLM Gateway ↗

  $0.09 / $0.58in / out per M

  0.17×of list price

• Novita

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

  Novita ↗

  $0.09 / $0.58in / out per M

  0.17×of list price

• Submodel

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

  262k context here

  $0.20 / $0.30in / out per M

  0.18×of list price

• Abacus

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

  262k context here

  $0.13 / $0.60in / out per M

  0.20×of list price

• Kilo Gateway

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

  262k context hereKilo Gateway ↗

  $0.15 / $0.60in / out per M

  0.21×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 ↗

  $0.15 / $0.75in / out per M

  0.24×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 ↗

  $0.15 / $0.75in / out per M

  0.24×of list price

• Nebius Token Factory

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

  262k context hereNebius Token Factory ↗

  $0.20 / $0.60in / out per M

  0.24×of list price

• Nscale

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

  33k context hereNscale ↗

  $0.20 / $0.60in / out per M

  0.24×of list price

• Nebius Token Factory

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

  262k context herefp8 precisionNebius Token Factory ↗

  $0.20 / $0.60in / out per M

  0.24×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 ↗

  $0.14 / $0.80in / out per M

  0.25×of list price

• Jiekou

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

  Jiekou ↗

  $0.15 / $0.80in / out per M

  0.26×of list price

• NanoGPT

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

  262k context hereNanoGPT ↗

  $0.30 / $0.50in / out per M

  0.29×of list price

• LLM Gateway

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

  41k context herefp8 precisionLLM Gateway ↗

  $0.20 / $0.80in / out per M

  0.29×of list price

• Novita

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

  41k context herefp8 precisionNovita ↗

  $0.20 / $0.80in / out per M

  0.29×of list price

• Hugging Face Inference Providers

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

  41k context hereHugging Face Inference Providers ↗

  $0.20 / $0.80in / out per M

  0.29×of list price

• Jiekou

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

  41k context herefp8 precisionJiekou ↗

  $0.20 / $0.80in / out per M

  0.29×of list price

• Requesty

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

  128k context herefp8 precisionRequesty ↗

  $0.20 / $0.80in / out per M

  0.29×of list price

• Crusoe

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

  262k context hereCrusoe ↗

  $0.22 / $0.80in / out per M

  0.30×of list price

showing the 25 cheapest of 34 · every row in the open dataset

• Scaleway

  7% above Alibaba Cloud's price.

  260k context hereScaleway ↗

  $0.75 / $2.25in / out per M

  0.92×of list price

• GreenPT

  47% above Alibaba Cloud's price.

  262k context here

  $1.03 / $3.08in / out per M

  1.26×of list price

• LLMTR

  57% above Alibaba Cloud's price.

  250k context hereLLMTR ↗

  $1.10 / $3.29in / out per M

  1.34×of list price

• Hyperbolic

  186% above Alibaba Cloud's price.

  Hyperbolic ↗

  $2 / $2in / out per M

  1.63×of list price