Call hosted models using managed inference capacity.
Check capabilities, credentials, costs, and required human setup. Read the integration instructions, then connect through the provider’s API, SDK, MCP, or CLI.
163 available services15 capability categoriesOpen discovery · no login
Choosing model inference for your task
Choose the model and serving mode for the required inputs, outputs and budget. Treat tool calls as proposed actions that your application must validate and execute.
Before you proceed: Check a representative task, malformed output and quota failure before relying on the model in an unattended workflow.
AI Agent Store editorial selection guidance. Check each listing’s official sources and setup requirements.
FIND THE MISSING CAPABILITY
Services with Model inference
7 services · Catalog updated 2026-11-10 · See each listing’s review date
Create a Fireworks account and API key, configure billing and choose a supported model and serving mode. Set an application budget and decide which tools the model may propose.
Our integration playbook Separate model inference from permission to execute a tool
Create an account and project, generate an API key, configure billing and choose the exact model and serving mode. Define the request budget and validate the model on the intended task.
Our integration playbook Choose the serving mode before committing to a latency-sensitive workflow
Create a Cloud Console organization and project, issue an API key and configure billing. Select an available model and check its capabilities, project limits and serving option.
Our integration playbook Budget output tokens against both inference spend and available quota
Create a Groq account and API key. Choose an available model and configure the organization’s tier, payment method and spend limits before production use.
Our integration playbook Coordinate model calls across agents sharing one organization
Create a workspace, choose or deploy the intended model or Workflow and obtain an API key. Confirm data permissions, model licensing, supported inputs and available credits.
Our integration playbook Validate the model on your scene before automating downstream decisions
Create a project, configure billing, application dependencies and model secrets, and choose compute and scaling settings. Prepare a tested application and the service-account credentials required for automated deployments.
Our integration playbook Test access control and resource limits alongside inference output
Create a Soniox account and project, configure billing and generate a project API key. Choose the appropriate regional endpoint and recorded-file or live-streaming workflow.
Our integration playbook Preserve audio evidence and job identity until the transcript is checked
Search for a capability, then follow the listing’s siteGuide link for our original integration playbook: selection advice, workflow, acceptance checks and recovery steps. The complete playbook is in the page HTML, so you can fetch it without JavaScript or a login.
GET /api/agent-services?capability=email
GET /api/agent-services?interface=mcp
GET /api/agent-services?payment=x402-wallet
GET /api/agent-services?payment=mpp-wallet
GET /api/agent-services?payment=no-payment
GET /api/agent-services?id=e2b
You are here to get something done. Find a mailbox for your messages, a browser for your web tasks, a sandbox for your code, or a wallet for approved payments.
Check what you need from your owner
Inspect the setup requirements before connecting. You may need your owner to create an account, grant OAuth consent, fund a wallet, or provide a website login.
Confirm your payment path
Check whether usage is free, billed to a provider account or uses a documented x402 or MPP wallet. “Not verified” means agent payment support has not been established. Confirm current terms and stay within your owner’s approved budget.