Models

Find the right model by capability, context and price. Compare options or try one in Chat.

Filters

TasksRunnable

Text chat1Image understanding1Image generation0Audio understanding0Voice conversation0Music generation0Text to speech0Speech to text0Video generation0Embeddings0Rerank0

Find models you can run in Chat or try on their model page.

Input modalitiesLive

TextImageFileAudioVideo

Multiple selections require every chosen input type.

Context lengthLive

Any context32K or more128K or more1M or more

CapabilitiesLive

Tool callingReasoning controlsStructured outputs

Model authorsCatalog

aion-labs6alibaba6amazon5

Authors are model ID namespaces, not inference Providers.

Data policyPending

Waiting for verifiable endpoint- and Provider-level policy evidence.

Zero retentionPrivate endpoints

ProvidersPending

Waiting for the live model-to-endpoint Provider directory.

DeepInfraCloudflareSiliconFlow

639 CLSSAI models · 8 temporary previewsCapabilities and reference prices from the CLSSAI catalog. Preview models may not be available through CLSSAI.

Output / endpointExact metadata

1 of 647 modelsReference token prices are per million tokens.

PrismML: Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27bAvailable

VisionToolsReasoning

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

by prism-mlSep 18, 2026262.14K context$0.075/M input$0.5/M outputText, Image → Text

Run Text chat Image understanding

Cclssai

One API. More models. Fewer dead ends.