Skip to content
    Live: Models

    Open models forproduction agents

    One OpenAI-compatible endpoint for reasoning, coding, multimodal, and low-latency workloads.20+ models serverless today. 90+ more as dedicated endpoints.

    Showing 117 models

    Gemma 4 26B A4B

    ServerlessGoogleChat

    Context

    256K

    Input

    $0.06/MTok

    Output

    $0.3/MTok

    Try it

    Mistral Nemo

    ServerlessMistralChat

    Context

    32K

    Input

    $0.018/MTok

    Output

    $0.03/MTok

    Recommended · Workflow automation
    Try it

    Gemma 4 31B IT

    ServerlessGoogleChat

    Context

    256K

    Input

    $0.1/MTok

    Output

    $0.35/MTok

    Recommended · Multimodal generation
    Try it

    Qwen3.6-35B-A3B

    ServerlessAlibabaChat

    Context

    256K

    Input

    $0.1/MTok

    Output

    $0.15/MTok

    Try it

    Nemotron 3 Super 120B A12B

    ServerlessNVIDIAChat

    Context

    256K

    Input

    $0.085/MTok

    Output

    $0.4/MTok

    Recommended · Research agents
    Try it

    Llama 3.1 8B Instruct

    ServerlessMetaChat

    Context

    128K

    Input

    $0.02/MTok

    Output

    $0.03/MTok

    Try it

    Qwen3.5 9B

    ServerlessAlibabaChat

    Context

    250K

    Input

    $0.1/MTok

    Output

    $0.15/MTok

    Try it

    BGE-M3

    ServerlessBAAIEmbeddings

    Context

    8K

    Input

    $0.01/MTok

    Recommended · Research agents+2
    Use via API

    Step 3.7 Flash

    ServerlessStepFunChat

    Context

    128K

    Input

    $0.2/MTok

    Output

    $1.15/MTok

    Try it

    Serverless pricing is the live Token Factory rate card, per million tokens unless otherwise noted, same rates as the Token Factory catalog. Dedicated endpoints are billed per GPU-hour. See pricing or compare options in serverless vs dedicated.

    Don't see a model you're interested in?

    Request a model