--- title: "AI Providers Supported by RewriteBar" description: "Explore the AI providers supported by RewriteBar, including OpenAI, Anthropic, Google Gemini, Ollama, oMLX, OpenRouter, Groq, and more." url: "https://rewritebar.com/docs/ai-providers" --- # AI Providers RewriteBar supports multiple AI providers, so you can pick the setup that fits your workflow. ## Choose the Right Model If you want guidance on speed vs quality, local model tradeoffs, and per-command overrides, see: - [Choosing the Right AI Model](https://rewritebar.com/docs/model-selection) ## Provider Directory Use this table to find: - whether a provider is cloud-hosted or local - quick links such as API console and provider website - whether provider-specific RewriteBar docs are available | Provider | Type | Links | Provider Docs | | --------------------- | ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ | | OpenAI | Cloud | [Console](https://platform.openai.com/) | [Guide](https://rewritebar.com/docs/ai-providers/openai) | | Anthropic | Cloud | [Console](https://platform.claude.com/) | [Guide](https://rewritebar.com/docs/ai-providers/anthropic) | | Google | Cloud | [Console](https://aistudio.google.com/) | [Guide](https://rewritebar.com/docs/ai-providers/gemini) | | Ollama | Local | [Website](https://ollama.com/) | [Guide](https://rewritebar.com/docs/ai-providers/ollama) | | Groq | Cloud | [Console](https://console.groq.com/) | [Guide](https://rewritebar.com/docs/ai-providers/groq) | | DeepSeek | Cloud | [Console](https://platform.deepseek.com/) | \- | | OpenRouter | Cloud | [Console](https://openrouter.ai/) | [Guide](https://rewritebar.com/docs/ai-providers/openrouter) | | Perplexity | Cloud | See provider docs | [Guide](https://rewritebar.com/docs/ai-providers/perplexity) | | GitHub Copilot | Cloud | [Website](https://github.com/features/copilot)[Token Guide](https://github.com/Alorse/copilot-to-api)[Proxy Option](https://github.com/lutzleonhardt/copilot-proxy) | [Guide](https://rewritebar.com/docs/ai-providers/github) | | Mistral | Cloud | [Console](https://mistral.ai/) | \- | | XAI | Cloud | [Console](https://x.ai/api) | \- | | TogetherAI | Cloud | [Console](https://www.together.ai/) | \- | | Azure AI Foundry | Cloud | [Console](https://azure.microsoft.com/products/ai-foundry) | \- | | LM Studio | Local | [Console](https://lmstudio.ai/)[Website](https://lmstudio.ai/) | \- | | Apple Intelligence | Local | [Website](https://developer.apple.com/documentation/foundationmodels) | \- | | Osaurus | Local | [Website](https://osaurus.ai/) | [Guide](https://rewritebar.com/docs/ai-providers/osaurus) | | oMLX | Local | [Website](https://github.com/jundot/omlx) | [Guide](https://rewritebar.com/docs/ai-providers/omlx) | | 302.AI | Cloud | [Console](https://help.302.ai/en/docs/ji-cheng-dao-OpenAI-guan-fang-SDK) | \- | | Amazon Bedrock | Cloud | [Console](https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html) | \- | | Baseten | Cloud | [Console](https://docs.baseten.co/development/model-apis/overview) | \- | | Cloudflare AI Gateway | Cloud | [Console](https://developers.cloudflare.com/ai-gateway/usage/chat-completion/) | \- | | Cortex | Cloud | [Console](https://cortex.so/docs/capabilities/embeddings/) | \- | | DeepInfra | Cloud | [Console](https://deepinfra.com/docs/openai%5Fapi) | \- | | Firmware | Cloud | [Console](https://voltagent.dev/models-docs/providers/firmware/) | \- | | Fireworks AI | Cloud | [Console](https://docs.fireworks.ai/tools-sdks/openai-compatibility) | \- | | Hugging Face | Cloud | [Console](https://huggingface.co/docs/inference-providers/tasks/chat-completion) | \- | | io.net | Cloud | [Console](https://io.net/docs/reference/ai-models/get-started-with-io-intelligence-api) | \- | | Moonshot AI | Cloud | [Console](https://platform.moonshot.ai/console/api-keys) | \- | | MiniMax | Cloud | [Console](https://platform.minimax.io/docs/api-reference/text-openai-api) | \- | | Nebius Token Factory | Cloud | [Console](https://docs.tokenfactory.nebius.com/api-reference/introduction) | \- | | OpenCode Zen | Cloud | [Console](https://opencode.ai/docs/zen) | \- | | OVHcloud AI Endpoints | Cloud | [Console](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/) | \- | | Scaleway | Cloud | [Console](https://www.scaleway.com/en/docs/managed-inference/reference-content/openai-compatibility/) | \- | | Venice AI | Cloud | [Console](https://docs.venice.ai/) | \- | | Vercel AI Gateway | Cloud | [Console](https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-compat) | \- | | Z.AI | Cloud | [Console](https://docs.z.ai/guides/develop/openai/python) | \- | | ZenMux | Cloud | [Console](https://docs.zenmux.ai/guide/quickstart) | \- | | Cerebras | Cloud | [Console](https://cloud.cerebras.ai/) | \- | Local providers such as Ollama, oMLX, and Apple Intelligence do not require a cloud API key. If authentication is enabled in oMLX, enter its server API key in RewriteBar. See the [oMLX setup guide](https://rewritebar.com/docs/ai-providers/omlx). ## Switching Providers You can easily switch between providers: 1. Go to **Settings** → **AI Providers** 2. Select your preferred provider 3. The change takes effect immediately ## Troubleshooting ### API Key Issues - Ensure your API key is valid and has sufficient credits - Check that the API key has the correct permissions ### Local AI Issues - Verify that your local server (Ollama, LM Studio, or oMLX) is running - Check the server URL and port - Ensure the model is loaded and accessible ### Performance Issues - Try a different model - Check your internet connection (for cloud providers) - Restart the local AI service (for local providers)