> For the complete documentation index, see [llms.txt](/llms.txt). > A full single-fetch corpus is available at [llms-full.txt](/llms-full.txt). --- title: AI providers description: Connect model API keys in Studio, then call provider-prefixed models from agents, prompts, and low-level generation code. last_verified: 2026-07-24 --- An **AI provider** integration stores the API key AGNT5 uses when your agents and prompts call a model API. You name models with a `"provider/model"` string, for example `"openai/gpt-4o-mini"` or `"anthropic/claude-3-5-sonnet-20241022"`. In managed deployments, configure provider keys in Studio so workers can resolve credentials without putting secrets in source code. ## Supported providers Studio exposes these AI provider integrations for project and workspace configuration: | Provider | Model prefix | API key env var | |---|---|---| | OpenAI | `openai` | `OPENAI_API_KEY` | | Anthropic | `anthropic` | `ANTHROPIC_API_KEY` | | Google AI | `google` or `gemini` | `GOOGLE_API_KEY` or `GEMINI_API_KEY` | | Groq | `groq` | `GROQ_API_KEY` | | OpenRouter | `openrouter` | `OPENROUTER_API_KEY` | | Mistral AI | `mistral` | `MISTRAL_API_KEY` | | DeepSeek | `deepseek` | `DEEPSEEK_API_KEY` | | xAI | `xai` | `XAI_API_KEY` | The Python and TypeScript SDKs also understand additional provider prefixes for local or advanced use, including `azure`, `bedrock`, `ollama`, `huggingface`, and `hf`. Those providers are not all exposed as first-class Studio integrations yet, so use ordinary environment configuration when you use them outside the Studio integration catalog. **Go:** The Go SDK has no `"provider/model"` string dispatch or `LM.provider()` namespace — each provider is its own constructor returning a `LanguageModel`: `agnt5.NewOpenAIModel`, `NewAnthropicModel`, `NewGoogleModel` (alias `NewGeminiModel`), `NewAzureOpenAIModel`, and the OpenAI-compatible `NewOpenRouterModel`, `NewGroqModel`, `NewDeepSeekModel`, `NewMistralModel`, `NewTogetherModel`, `NewXAIModel`, `NewMoonshotModel`, `NewOllamaModel` (all of the OpenAI-compatible ones take `agnt5.OpenAIConfig{Model: "..."}`). There's no built-in Bedrock or Hugging Face constructor yet. ## Configure credentials For local development, set the provider API key before your worker starts: ```bash export OPENAI_API_KEY=sk-... export ANTHROPIC_API_KEY=sk-ant-... export GOOGLE_API_KEY=... export GROQ_API_KEY=... export OPENROUTER_API_KEY=... export MISTRAL_API_KEY=... export DEEPSEEK_API_KEY=... export XAI_API_KEY=... ``` For deployed workers, store provider keys in Studio: 1. Open your project in Studio. 2. Open **Settings** -> **Integrations**. 3. Add the provider integration and paste the API key. 4. Choose the narrowest scope that works: workspace, project, or environment-specific secret. Your code should not pass raw provider keys. AGNT5 injects the credential into the worker environment or resolves it through the managed credential path at runtime. ## Use a provider in an agent Create an agent with a provider-prefixed model string. To change providers, change the model string and make sure the matching credential is configured. **Python:** ```python from agnt5 import Agent agent = Agent( name="summarizer", model="openai/gpt-4o-mini", instructions="Summarize articles into three concise bullet points.", ) result = await agent.run("Summarize the product launch notes.") print(result.output) ``` The same pattern works with another provider: ```python from agnt5 import Agent agent = Agent( name="summarizer", model="anthropic/claude-3-5-sonnet-20241022", instructions="Summarize articles into three concise bullet points.", ) ``` **TypeScript:** ```typescript const agent = new Agent({ name: 'summarizer', model: LM.openai(), modelName: 'openai/gpt-4o-mini', instructions: 'Summarize articles into three concise bullet points.', }); const result = await agent.run('Summarize the product launch notes.'); console.log(result.output); ``` The same pattern works with another provider — swap the `LM` client and `modelName`: ```typescript const agent = new Agent({ name: 'summarizer', model: LM.anthropic(), modelName: 'anthropic/claude-3-5-sonnet-20241022', instructions: 'Summarize articles into three concise bullet points.', }); ``` **Go:** ```go const lm = LM.openai(); const response = await lm.generate({ model: 'openai/gpt-4o-mini', messages: [ { role: 'user', content: 'Write a one-paragraph incident summary for a resolved API outage.' }, ], }); console.log(response.text); ``` **Go:** Call `Generate` directly on a model, or `ctx.Generate(model, request)` from inside a function/workflow/tool handler: ```go model := agnt5.NewOpenAIModel(agnt5.OpenAIConfig{ APIKey: os.Getenv("OPENAI_API_KEY"), Model: "gpt-4o-mini", }) response, err := model.Generate(ctx, agnt5.GenerateRequest{ Messages: []agnt5.Message{ {Role: agnt5.MessageRoleUser, Content: "Write a one-paragraph incident summary for a resolved API outage."}, }, }) fmt.Println(response.Content) ``` The `model` value still uses the same `"provider/model"` format, and the provider key still comes from the environment or the configured integration. The `model` value still uses the same `"provider/model"` format, and the provider key still comes from the environment or the configured integration. The Go SDK has no equivalent environment/integration auto-resolution — always set `APIKey` explicitly on the provider config, as shown above. ## Provider-hosted tools Provider-hosted tools run on the model provider's infrastructure. AGNT5 sends the tool request to the provider and records the result in the model response; your worker does not execute local tool code for these calls. **Python:** ```python from agnt5 import Agent from agnt5.lm import BuiltInTool agent = Agent( name="researcher", model="openai/gpt-4o-mini", instructions="Use web search for current facts before answering.", built_in_tools=[BuiltInTool.WEB_SEARCH], ) result = await agent.run("What changed in the latest product release?") print(result.output) ``` | Tool | What it does | Providers | |---|---|---| | `BuiltInTool.WEB_SEARCH` | Live web search with provider-returned results | OpenAI, Anthropic, Google | | `BuiltInTool.CODE_INTERPRETER` | Run code in a provider-hosted sandbox | OpenAI | | `BuiltInTool.FILE_SEARCH` | Search files hosted by the provider | OpenAI | | `BuiltInTool.WEB_FETCH` | Fetch the content of a specific URL | Anthropic | **TypeScript:** ```typescript const agent = new Agent({ name: 'researcher', model: LM.openai(), modelName: 'openai/gpt-4o-mini', instructions: 'Use web search for current facts before answering.', builtInTools: ['web_search'], }); const result = await agent.run('What changed in the latest product release?'); console.log(result.output); ``` | Tool | What it does | Providers | |---|---|---| | `'web_search'` | Live web search with provider-returned results | OpenAI, Anthropic, Google | | `'code_interpreter'` | Run code in a provider-hosted sandbox | OpenAI | | `'file_search'` | Search files hosted by the provider | OpenAI | | `'web_fetch'` | Fetch the content of a specific URL | Anthropic | **Go:** Not yet available in the Go SDK — there's no `built_in_tools`/`builtInTools` equivalent, so provider-hosted web search, code interpreter, file search, or URL fetch tools aren't exposed. Write a custom tool (see [Tools](/docs/build/tools.md)) that calls the provider's API directly if you need this capability today. You can mix provider-hosted tools with AGNT5 custom tools on the same agent. See [Tools](/docs/build/tools.md) for custom tools, sandbox workspaces, and human-in-the-loop tools. ## Next steps - [Agents](/docs/build/agents.md): configure model-backed reasoning loops. - [Prompts](/docs/build/prompts.md): run managed prompts with provider-backed models. - [Tools](/docs/build/tools.md): add custom, sandbox, and provider-hosted capabilities. - [Deploying](/docs/run/deploying.md): deploy workers with integrations and secrets configured.