> ## Documentation Index > Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Model Providers > Setup guides for model providers and API adapters available in Agno. Browse the provider guides available in this documentation. Capabilities vary by provider endpoint and model ID. ## Provider APIs > **[Anthropic](https://agno-v2.mintlify.site/models/providers/native/anthropic/overview.md)** > > Call Anthropic's Messages API with Claude models. > **[Cohere](https://agno-v2.mintlify.site/models/providers/native/cohere/overview.md)** > > Call Cohere's Chat API with Command models. > **[DashScope](https://agno-v2.mintlify.site/models/providers/native/dashscope/overview.md)** > > Run Qwen models through Alibaba Cloud DashScope. > **[DeepSeek](https://agno-v2.mintlify.site/models/providers/native/deepseek/overview.md)** > > Send chat and reasoning requests to DeepSeek. > **[Google Gemini](https://agno-v2.mintlify.site/models/providers/native/google/overview.md)** > > Generate content with Google's Gemini API. > **[Google Gemini Interactions](https://agno-v2.mintlify.site/models/providers/native/google/gemini-interactions.md)** > > Google's stateful Interactions API and managed agents. > **[Inception](https://agno-v2.mintlify.site/models/providers/native/inception/overview.md)** > > Inception Labs Mercury diffusion models. > **[Meta](https://agno-v2.mintlify.site/models/providers/native/meta/overview.md)** > > Meta Llama native and OpenAI-compatible adapters. > **[MiniMax](https://agno-v2.mintlify.site/models/providers/native/minimax/overview.md)** > > Send OpenAI-compatible requests to MiniMax. > **[Mistral](https://agno-v2.mintlify.site/models/providers/native/mistral/overview.md)** > > Call Mistral's Chat Completions API. > **[OpenAI Chat Completions](https://agno-v2.mintlify.site/models/providers/native/openai/completion/overview.md)** > > Use OpenAI's Chat Completions interface. > **[OpenAI Responses](https://agno-v2.mintlify.site/models/providers/native/openai/responses/overview.md)** > > Use OpenAI's Responses interface and built-in tools. > **[Perplexity](https://agno-v2.mintlify.site/models/providers/native/perplexity/overview.md)** > > Run Perplexity Sonar models and retain URL citations. > **[Vercel v0](https://agno-v2.mintlify.site/models/providers/native/vercel/overview.md)** > > Vercel v0 models for web application generation. > **[xAI](https://agno-v2.mintlify.site/models/providers/native/xai/overview.md)** > > Run Grok models through xAI. > **[Xiaomi MiMo](https://agno-v2.mintlify.site/models/providers/native/xiaomi/overview.md)** > > Send OpenAI-compatible requests to Xiaomi MiMo. ## Local Runtimes > **[llama.cpp](https://agno-v2.mintlify.site/models/providers/local/llama-cpp/overview.md)** > > Local GGUF model inference with llama.cpp. > **[LM Studio](https://agno-v2.mintlify.site/models/providers/local/lmstudio/overview.md)** > > Connect to LM Studio's local model server. > **[Ollama](https://agno-v2.mintlify.site/models/providers/local/ollama/overview.md)** > > Ollama Chat and Responses API adapters. > **[vLLM](https://agno-v2.mintlify.site/models/providers/local/vllm/overview.md)** > > vLLM high-throughput inference. ## Cloud Platforms > **[AWS Bedrock](https://agno-v2.mintlify.site/models/providers/cloud/aws-bedrock/overview.md)** > > Call models through the Amazon Bedrock Converse API. > **[Claude via AWS Bedrock](https://agno-v2.mintlify.site/models/providers/cloud/aws-claude/overview.md)** > > Anthropic Claude models via AWS Bedrock. > **[Azure AI Foundry](https://agno-v2.mintlify.site/models/providers/cloud/azure-ai-foundry/overview.md)** > > Connect to Azure AI Foundry inference endpoints. > **[Azure AI Foundry Claude](https://agno-v2.mintlify.site/models/providers/cloud/azure-foundry-claude/overview.md)** > > Anthropic Claude models via Azure AI Foundry. > **[Azure OpenAI](https://agno-v2.mintlify.site/models/providers/cloud/azure-openai/overview.md)** > > Connect to an Azure OpenAI deployment. > **[Vertex AI Claude](https://agno-v2.mintlify.site/models/providers/cloud/vertexai-claude/overview.md)** > > Anthropic Claude models via Google Vertex AI. > **[IBM WatsonX](https://agno-v2.mintlify.site/models/providers/cloud/ibm-watsonx/overview.md)** > > Run foundation models through IBM watsonx.ai. ## Hosted Inference and Gateways > **[AI/ML API](https://agno-v2.mintlify.site/models/providers/gateways/aimlapi/overview.md)** > > Route OpenAI-compatible requests through AI/ML API. > **[Cerebras](https://agno-v2.mintlify.site/models/providers/gateways/cerebras/overview.md)** > > Call Cerebras models with the native SDK. > **[Cerebras OpenAI](https://agno-v2.mintlify.site/models/providers/gateways/cerebras-openai/overview.md)** > > Call Cerebras through its OpenAI-compatible endpoint. > **[Cloudflare](https://agno-v2.mintlify.site/models/providers/gateways/cloudflare/overview.md)** > > Cloudflare AI Gateway unified API. > **[CometAPI](https://agno-v2.mintlify.site/models/providers/gateways/cometapi/overview.md)** > > Route OpenAI-compatible requests through CometAPI. > **[DeepInfra](https://agno-v2.mintlify.site/models/providers/gateways/deepinfra/overview.md)** > > Send OpenAI-compatible requests to DeepInfra. > **[Fireworks](https://agno-v2.mintlify.site/models/providers/gateways/fireworks/overview.md)** > > Send OpenAI-compatible requests to Fireworks AI. > **[Groq](https://agno-v2.mintlify.site/models/providers/gateways/groq/overview.md)** > > Run hosted models through GroqCloud. > **[Hugging Face](https://agno-v2.mintlify.site/models/providers/gateways/huggingface/overview.md)** > > Call models through Hugging Face Inference Providers. > **[LangDB](https://agno-v2.mintlify.site/models/providers/gateways/langdb/overview.md)** > > Route model requests through LangDB. > **[LiteLLM](https://agno-v2.mintlify.site/models/providers/gateways/litellm/overview.md)** > > LiteLLM unified model interface. > **[LiteLLM OpenAI](https://agno-v2.mintlify.site/models/providers/gateways/litellm-openai/overview.md)** > > Connect to a LiteLLM OpenAI-compatible endpoint. > **[Nebius Token Factory](https://agno-v2.mintlify.site/models/providers/gateways/nebius/overview.md)** > > Run hosted models through Nebius Token Factory. > **[Neosantara](https://agno-v2.mintlify.site/models/providers/gateways/neosantara/overview.md)** > > Send OpenAI-compatible requests to Neosantara. > **[Nexus](https://agno-v2.mintlify.site/models/providers/gateways/nexus/overview.md)** > > Route model requests through Nexus. > **[NVIDIA](https://agno-v2.mintlify.site/models/providers/gateways/nvidia/overview.md)** > > Connect to NVIDIA-hosted model endpoints. > **[OpenRouter](https://agno-v2.mintlify.site/models/providers/gateways/openrouter/overview.md)** > > OpenRouter Chat Completions and Responses API adapters. > **[Portkey](https://agno-v2.mintlify.site/models/providers/gateways/portkey/overview.md)** > > Route requests through the Portkey AI Gateway. > **[Requesty](https://agno-v2.mintlify.site/models/providers/gateways/requesty/overview.md)** > > Route model requests through Requesty. > **[SambaNova](https://agno-v2.mintlify.site/models/providers/gateways/sambanova/overview.md)** > > Run hosted models through SambaNova Cloud. > **[SiliconFlow](https://agno-v2.mintlify.site/models/providers/gateways/siliconflow/overview.md)** > > Send OpenAI-compatible requests to SiliconFlow. > **[Together](https://agno-v2.mintlify.site/models/providers/gateways/together/overview.md)** > > Run hosted models through Together AI. > **[Tuning Engines](https://agno-v2.mintlify.site/models/providers/gateways/tuning-engines/overview.md)** > > Connect to a governed OpenAI-compatible endpoint. ## Model String Key Catalog These are the canonical provider keys registered by the v2.7.2 model-string resolver. Similar keys can select different API adapters. | Category | Canonical keys | | - | - | | Provider APIs | `anthropic`, `cohere`, `dashscope`, `deepseek`, `google`, `google-interactions`, `inception`, `internlm`, `llama-openai`, `meta`, `minimax`, `mistral`, `moonshot`, `open-responses`, `openai`, `openai-chat`, `openai-responses`, `perplexity`, `vercel`, `xai`, `xiaomi` | | Local runtimes | `llama-cpp`, `lmstudio`, `ollama`, `ollama-responses`, `vllm` | | Cloud platforms | `aws-bedrock`, `aws-claude`, `azure-ai-foundry`, `azure-foundry-claude`, `azure-openai`, `ibm`, `vertexai-claude` | | Hosted inference and gateways | `aimlapi`, `cerebras`, `cerebras-openai`, `cloudflare`, `cometapi`, `deepinfra`, `fireworks`, `groq`, `huggingface`, `langdb`, `litellm`, `litellm-openai`, `n1n`, `nebius`, `neosantara`, `nexus`, `nvidia`, `openrouter`, `openrouter-responses`, `portkey`, `requesty`, `sambanova`, `siliconflow`, `together`, `tuning-engines` | Use canonical keys in new configuration. See [Model as String](https://agno-v2.mintlify.site/models/model-as-string.md) for parsing rules and API-variant examples. ## SDK Adapters Without Dedicated Guides The SDK also exports these provider adapters, but this documentation does not yet include setup guides for them: | Adapter | Import | Related documentation | | - | - | - | | InternLM | `from agno.models.internlm import InternLM` | [InternLM reference](https://agno-v2.mintlify.site/reference/models/internlm.md) | | Moonshot | `from agno.models.moonshot import MoonShot` | [Moonshot examples](https://agno-v2.mintlify.site/examples/models/moonshot/overview.md) | | N1N | `from agno.models.n1n import N1N` | [N1N reference](https://agno-v2.mintlify.site/reference/models/n1n.md) | > [!WARNING] > > In v2.7.2, the `InternLM` default `base_url` already ends in `/chat/completions`, and the inherited OpenAI client appends that route again. The `internlm:model_id` string therefore sends requests to a duplicated path. Until the adapter is fixed, instantiate the class with `base_url="https://internlm-chat.intern-ai.org.cn/puyu/api/v1"` instead of using the string form. Feature support still depends on the selected model ID and endpoint. Verify both before deployment. ## Developer Resources * [OpenAI-compatible and Open Responses adapters](https://agno-v2.mintlify.site/models/providers/openai-like.md) * [Compatibility overview](https://agno-v2.mintlify.site/models/compatibility.md) * [Base model reference](https://agno-v2.mintlify.site/reference/models/model.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.