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
Call Anthropic's Messages API with Claude models.
Cohere
Call Cohere's Chat API with Command models.
DashScope
Run Qwen models through Alibaba Cloud DashScope.
DeepSeek
Send chat and reasoning requests to DeepSeek.
Google Gemini
Generate content with Google's Gemini API.
Google Gemini Interactions
Google's stateful Interactions API and managed agents.
Inception
Inception Labs Mercury diffusion models.
Meta
Meta Llama native and OpenAI-compatible adapters.
MiniMax
Send OpenAI-compatible requests to MiniMax.
Mistral
Call Mistral's Chat Completions API.
OpenAI Chat Completions
Use OpenAI's Chat Completions interface.
OpenAI Responses
Use OpenAI's Responses interface and built-in tools.
Perplexity
Run Perplexity Sonar models and retain URL citations.
Vercel v0
Vercel v0 models for web application generation.
xAI
Run Grok models through xAI.
Xiaomi MiMo
Send OpenAI-compatible requests to Xiaomi MiMo.
Local Runtimes
Llmman
Connect to llmman for local OpenAI-compatible inference.
llama.cpp
Local GGUF model inference with llama.cpp.
LM Studio
Connect to LM Studio's local model server.
Ollama
Ollama Chat and Responses API adapters.
vLLM
vLLM high-throughput inference.
Cloud Platforms
AWS Bedrock
Call models through the Amazon Bedrock Converse API.
Claude via AWS Bedrock
Anthropic Claude models via AWS Bedrock.
Azure AI Foundry
Connect to Azure AI Foundry inference endpoints.
Azure AI Foundry Claude
Anthropic Claude models via Azure AI Foundry.
Azure OpenAI
Connect to an Azure OpenAI deployment.
Vertex AI Claude
Anthropic Claude models via Google Vertex AI.
IBM WatsonX
Run foundation models through IBM watsonx.ai.
Hosted Inference and Gateways
AI/ML API
Route OpenAI-compatible requests through AI/ML API.
Cerebras
Call Cerebras models with the native SDK.
Cerebras OpenAI
Call Cerebras through its OpenAI-compatible endpoint.
Cloudflare
Cloudflare AI Gateway unified API.
CometAPI
Route OpenAI-compatible requests through CometAPI.
DeepInfra
Send OpenAI-compatible requests to DeepInfra.
Fireworks
Send OpenAI-compatible requests to Fireworks AI.
Groq
Run hosted models through GroqCloud.
Hugging Face
Call models through Hugging Face Inference Providers.
LangDB
Route model requests through LangDB.
LiteLLM
LiteLLM unified model interface.
LiteLLM OpenAI
Connect to a LiteLLM OpenAI-compatible endpoint.
Nebius Token Factory
Run hosted models through Nebius Token Factory.
Neosantara
Send OpenAI-compatible requests to Neosantara.
Nexus
Route model requests through Nexus.
NVIDIA
Connect to NVIDIA-hosted model endpoints.
OpenRouter
OpenRouter Chat Completions and Responses API adapters.
Portkey
Route requests through the Portkey AI Gateway.
Requesty
Route model requests through Requesty.
SambaNova
Run hosted models through SambaNova Cloud.
SiliconFlow
Send OpenAI-compatible requests to SiliconFlow.
Together
Run hosted models through Together AI.
Tuning Engines
Connect to a governed OpenAI-compatible endpoint.
Model String Key Catalog
These are the canonical provider keys registered by the 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, xai-responses, xiaomi |
| Local runtimes | llama-cpp, llmman, 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, ramp, requesty, sambanova, siliconflow, synthorai, tokenlab, together, trustedrouter, tuning-engines |
Use canonical keys in new configuration. See Model as String 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 |
| Moonshot | from agno.models.moonshot import MoonShot | Moonshot examples |
| N1N | from agno.models.n1n import N1N | N1N reference |
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.