Models

AkashML hosts a curated set of open source AI models served via the Akash Network's decentralized GPU infrastructure. All models are accessible through the OpenAI-compatible REST API at api.akashml.com.

Available models and pricing

Pass the Model ID as the model field in your request. The same list is returned by the /v1/models endpoint and shown in the Playground sidebar.

Cache-read rates are set per model. A — in the Cache read column means that model has no cache-read rate, so all of its input tokens bill at the full input rate — unless the note below the table says cache-read rates aren't being shown, in which case query /v1/models directly.

Text models — per 1M tokens

Token rates are per 1M tokens and subject to change. See how pricing is calculated for the billing formulas.

Selecting a model

In the Playground, open the model selector in the sidebar to browse available models. You can filter by capability or context length.

In the API, specify the model in the request body:

{
  "model": "zai-org/GLM-5.2",
  "messages": [{ "role": "user", "content": "Hello!" }]
}

Model parameters

Each model exposes a subset of the following parameters:

Pricing

Credits are consumed per token for the text models above, and per request for image models. For the exact formulas — including how cached input tokens are discounted on the models that support it, and how per-request pricing is computed — see How pricing is calculated.