Together AI Provider Setup and Model Selection

This page covers how to set up the Together AI provider in OpenClaw, including authentication and model selection. It is intended for developers integrating open-source models via the Together API.

Read this when

  • You want to use Together AI with OpenClaw
  • You need the API key env var or CLI auth choice

Together AI gives you access to leading open-source models like Llama, DeepSeek, Kimi, and others through a single API. OpenClaw bundles it as the together provider.

PropertyValue
Providertogether
AuthTOGETHER_API_KEY
APIOpenAI-compatible
Base URLhttps://api.together.xyz/v1

Getting started

Get an API key

Generate an API key at api.together.ai/settings/api-keys.

Run onboarding

openclaw onboard --auth-choice together-api-key

Set a default model

{
  agents: {
    defaults: {
      model: {
        primary: "together/meta-llama/Llama-3.3-70B-Instruct-Turbo",
      },
    },
  },
}

Non-interactive example

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice together-api-key \
  --together-api-key "$TOGETHER_API_KEY"

Note

Onboarding sets together/meta-llama/Llama-3.3-70B-Instruct-Turbo as the default model.

Built-in catalog

Cost is USD per million tokens.

Model refNameInputContextMax outputCost (in/out)Notes
together/meta-llama/Llama-3.3-70B-Instruct-TurboLlama 3.3 70B Instruct Turbotext131,0728,1920.88 / 0.88Default model
together/moonshotai/Kimi-K2.6Kimi K2.6 FP4text, image262,14432,7681.20 / 4.50Reasoning model
together/deepseek-ai/DeepSeek-V4-ProDeepSeek V4 Protext512,0008,1922.10 / 4.40Reasoning model
together/Qwen/Qwen2.5-7B-Instruct-TurboQwen2.5 7B Instruct Turbotext32,7688,1920.30 / 0.30Fast, non-reasoning
together/zai-org/GLM-5.1GLM 5.1 FP4text202,7528,1921.40 / 4.40Reasoning model

Video generation

The bundled together plugin also registers video generation through the shared video_generate tool.

PropertyValue
Default video modelWan-AI/Wan2.2-T2V-A14B
Other modelsWan-AI/Wan2.2-I2V-A14B, minimax/hailuo-02, kwaivgI/kling-2.1-master
Modestext-to-video; image-to-video only with Wan-AI/Wan2.2-I2V-A14B (single reference image)
Duration1-10 seconds
Supported parameterssize (parsed as <width>x<height>); aspectRatio/resolution are not read

To use Together as the default video provider:

{
  agents: {
    defaults: {
      videoGenerationModel: {
        primary: "together/Wan-AI/Wan2.2-T2V-A14B",
      },
    },
  },
}

Tip

See Video generation for the shared tool parameters, provider selection, and failover behavior.

Environment note

If the Gateway runs as a daemon (launchd/systemd), make sure TOGETHER_API_KEY is available to that process (for example, in ~/.openclaw/.env or via env.shellEnv).

Warning

Keys set only in your interactive shell are not visible to daemon-managed gateway processes. Use ~/.openclaw/.env or env.shellEnv config for persistent availability.

Troubleshooting

  • Verify your key works: openclaw models list --provider together
  • If models are not appearing, confirm the API key is set in the correct environment for your Gateway process.
  • Model refs use the form together/<model-id>.