Together AI Provider Setup

Together AI offers a unified API for several prominent open-source models, such as Llama, DeepSeek, Kimi, and others. Within OpenClaw, it is included as the together provider.

Property	Value
Provider	`together`
Auth	`TOGETHER_API_KEY`
API	OpenAI-compatible
Base URL	`https://api.together.xyz/v1`

Getting started

Get an API key

To get started, generate an API key through api.together.ai/settings/api-keys.

Run onboarding

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

Set a default model

{
  agents: {
    defaults: {
      model: {
        primary: "together/moonshotai/Kimi-K2.6",
      },
    },
  },
}

Non-interactive example

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

Note

During onboarding, the default chat model is set to Together's recommended option, together/moonshotai/Kimi-K2.6.

Built-in catalog

Pricing is expressed in USD per million tokens.

Model ref	Name	Input	Context	Max output	Cost (in/out)	Notes
`together/meta-llama/Llama-3.3-70B-Instruct-Turbo`	Llama 3.3 70B Instruct Turbo	text	131,072	8,192	1.04 / 1.04	General model
`together/moonshotai/Kimi-K2.6`	Kimi K2.6 FP4	text, image	262,144	32,768	1.20 / 4.50	Default model
`together/deepseek-ai/DeepSeek-V4-Pro`	DeepSeek V4 Pro	text	512,000	384,000	1.74 / 3.48	Reasoning model
`together/zai-org/GLM-5.2`	GLM 5.2 FP4	text	262,144	131,072	1.40 / 4.40	Reasoning model

Video generation

Video generation is also registered by the bundled together plugin, which relies on the shared video_generate tool.

Property	Value
Default video model	`Wan-AI/Wan2.2-T2V-A14B`
Other models	`Wan-AI/Wan2.2-I2V-A14B`, `minimax/hailuo-02`, `kwaivgI/kling-2.1-master`
Modes	text-to-video; image-to-video only with `Wan-AI/Wan2.2-I2V-A14B` (single reference image)
Duration	1-10 seconds
Supported parameters	`size` (parsed as `<width>x<height>`); `aspectRatio`/`resolution` are not read

For making Together your default video provider:

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

Tip

The shared tool parameters, provider selection, and failover behavior are detailed in Video generation.

Environment note

When the Gateway operates as a daemon (launchd/systemd), ensure that TOGETHER_API_KEY is accessible to that process, for instance through ~/.openclaw/.env or env.shellEnv.

Warning

Keys configured solely in your interactive shell remain hidden from daemon-managed gateway processes. For persistent availability, rely on ~/.openclaw/.env or env.shellEnv config.

Troubleshooting

Validate your key with: openclaw models list --provider together
If models fail to show up, verify that the API key is present in the right environment for your Gateway process.
Model refs follow the pattern together/<model-id>.

Model providers, Provider rules, model refs, and failover behavior.
Video generation, Shared video generation tool parameters and provider selection.
Configuration reference, Full config schema including provider settings.
Together AI, Together AI dashboard, API docs, and pricing.