2026-01-11 02:27:30 +01:00
|
|
|
---
|
2026-02-08 03:14:07 +00:00
|
|
|
summary: "Model providers (LLMs) supported by OpenClaw"
|
2026-01-11 02:27:30 +01:00
|
|
|
read_when:
|
2026-01-13 06:16:43 +00:00
|
|
|
- You want to choose a model provider
|
|
|
|
|
- You need a quick overview of supported LLM backends
|
2026-02-08 03:14:07 +00:00
|
|
|
title: "Model Providers"
|
2026-01-11 02:27:30 +01:00
|
|
|
---
|
2026-01-31 21:13:13 +09:00
|
|
|
|
2026-01-13 06:16:43 +00:00
|
|
|
# Model Providers
|
2026-01-11 02:27:30 +01:00
|
|
|
|
2026-01-30 03:15:10 +01:00
|
|
|
OpenClaw can use many LLM providers. Pick a provider, authenticate, then set the
|
2026-01-13 06:16:43 +00:00
|
|
|
default model as `provider/model`.
|
2026-01-11 02:27:30 +01:00
|
|
|
|
2026-01-23 00:19:23 +00:00
|
|
|
Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See [Channels](/channels).
|
2026-01-13 08:25:22 +00:00
|
|
|
|
2026-01-29 15:31:48 -08:00
|
|
|
## Highlight: Venice (Venice AI)
|
2026-01-25 01:49:31 +00:00
|
|
|
|
2026-01-29 15:31:48 -08:00
|
|
|
Venice is our recommended Venice AI setup for privacy-first inference with an option to use Opus for hard tasks.
|
2026-01-25 01:49:31 +00:00
|
|
|
|
|
|
|
|
- Default: `venice/llama-3.3-70b`
|
|
|
|
|
- Best overall: `venice/claude-opus-45` (Opus remains the strongest)
|
|
|
|
|
|
|
|
|
|
See [Venice AI](/providers/venice).
|
|
|
|
|
|
2026-01-13 06:16:43 +00:00
|
|
|
## Quick start
|
2026-01-11 02:27:30 +01:00
|
|
|
|
2026-01-31 21:13:13 +09:00
|
|
|
1. Authenticate with the provider (usually via `openclaw onboard`).
|
|
|
|
|
2. Set the default model:
|
2026-01-11 02:27:30 +01:00
|
|
|
|
2026-01-13 06:16:43 +00:00
|
|
|
```json5
|
|
|
|
|
{
|
2026-02-08 03:14:07 +00:00
|
|
|
agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
|
2026-01-13 06:16:43 +00:00
|
|
|
}
|
|
|
|
|
```
|
2026-01-11 02:27:30 +01:00
|
|
|
|
2026-01-13 06:16:43 +00:00
|
|
|
## Provider docs
|
|
|
|
|
|
|
|
|
|
- [OpenAI (API + Codex)](/providers/openai)
|
2026-01-14 20:06:32 +00:00
|
|
|
- [Anthropic (API + Claude Code CLI)](/providers/anthropic)
|
2026-01-17 20:28:15 +00:00
|
|
|
- [Qwen (OAuth)](/providers/qwen)
|
2026-01-13 06:16:43 +00:00
|
|
|
- [OpenRouter](/providers/openrouter)
|
Feat/litellm provider (#12823)
* feat: add LiteLLM provider types, env var, credentials, and auth choice
Add litellm-api-key auth choice, LITELLM_API_KEY env var mapping,
setLitellmApiKey() credential storage, and LITELLM_DEFAULT_MODEL_REF.
* feat: add LiteLLM onboarding handler and provider config
Add applyLitellmProviderConfig which properly registers
models.providers.litellm with baseUrl, api type, and model definitions.
This fixes the critical bug from PR #6488 where the provider entry was
never created, causing model resolution to fail at runtime.
* docs: add LiteLLM provider documentation
Add setup guide covering onboarding, manual config, virtual keys,
model routing, and usage tracking. Link from provider index.
* docs: add LiteLLM to sidebar navigation in docs.json
Add providers/litellm to both English and Chinese provider page lists
so the docs page appears in the sidebar navigation.
* test: add LiteLLM non-interactive onboarding test
Wire up litellmApiKey flag inference and auth-choice handler for the
non-interactive onboarding path, and add an integration test covering
profile, model default, and credential storage.
* fix: register --litellm-api-key CLI flag and add preferred provider mapping
Wire up the missing Commander CLI option, action handler mapping, and
help text for --litellm-api-key. Add litellm-api-key to the preferred
provider map for consistency with other providers.
* fix: remove zh-CN sidebar entry for litellm (no localized page yet)
* style: format buildLitellmModelDefinition return type
* fix(onboarding): harden LiteLLM provider setup (#12823)
* refactor(onboarding): keep auth-choice provider dispatcher under size limit
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-02-11 02:46:56 -08:00
|
|
|
- [LiteLLM (unified gateway)](/providers/litellm)
|
2026-01-16 14:40:56 +01:00
|
|
|
- [Vercel AI Gateway](/providers/vercel-ai-gateway)
|
2026-02-10 00:49:34 +01:00
|
|
|
- [Together AI](/providers/together)
|
2026-02-04 04:10:13 -08:00
|
|
|
- [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
|
2026-01-31 06:04:10 +01:00
|
|
|
- [Moonshot AI (Kimi + Kimi Coding)](/providers/moonshot)
|
2026-02-22 19:03:56 -05:00
|
|
|
- [Mistral](/providers/mistral)
|
2026-01-13 06:16:43 +00:00
|
|
|
- [OpenCode Zen](/providers/opencode)
|
2026-02-07 15:40:35 -05:00
|
|
|
- [Amazon Bedrock](/providers/bedrock)
|
2026-01-13 06:16:43 +00:00
|
|
|
- [Z.AI](/providers/zai)
|
2026-01-29 00:30:17 +08:00
|
|
|
- [Xiaomi](/providers/xiaomi)
|
2026-01-13 06:16:43 +00:00
|
|
|
- [GLM models](/providers/glm)
|
|
|
|
|
- [MiniMax](/providers/minimax)
|
2026-01-29 15:31:48 -08:00
|
|
|
- [Venice (Venice AI, privacy-focused)](/providers/venice)
|
2026-02-13 16:18:16 +01:00
|
|
|
- [Hugging Face (Inference)](/providers/huggingface)
|
2026-01-24 22:38:52 +00:00
|
|
|
- [Ollama (local models)](/providers/ollama)
|
2026-02-09 10:20:45 +00:00
|
|
|
- [vLLM (local models)](/providers/vllm)
|
2026-02-05 13:35:35 +08:00
|
|
|
- [Qianfan](/providers/qianfan)
|
2026-02-08 03:08:41 +00:00
|
|
|
- [NVIDIA](/providers/nvidia)
|
2026-01-13 06:16:43 +00:00
|
|
|
|
2026-01-17 08:46:40 +00:00
|
|
|
## Transcription providers
|
|
|
|
|
|
|
|
|
|
- [Deepgram (audio transcription)](/providers/deepgram)
|
|
|
|
|
|
2026-01-25 22:32:38 -06:00
|
|
|
## Community tools
|
|
|
|
|
|
|
|
|
|
- [Claude Max API Proxy](/providers/claude-max-api-proxy) - Use Claude Max/Pro subscription as an OpenAI-compatible API endpoint
|
|
|
|
|
|
2026-01-13 06:16:43 +00:00
|
|
|
For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration,
|
|
|
|
|
see [Model providers](/concepts/model-providers).
|