Get started

AI/ML API for AI agents

AI/ML API is a unified API for accessing many AI models for text, image and other generative tasks. Developers use it to call multiple model providers through one integration. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect AI/ML APISee the 30 actions ↓
AI and modelsAPI keyMCP + RESTaimlapi.com
AUDIT LOG · AI/ML APIPOLICY: acme-support
09:41:07 · claude · u_8f2read
ai_ml_api.list_runs
List Runs✓ allowed · 212ms
09:41:08 · claude · u_8f2read
ai_ml_api.get_run
Get Run✓ allowed · 164ms
09:41:09 · claude · u_8f2write
ai_ml_api.create_run
Create Run✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
ai_ml_api.delete_thread
Delete Thread✕ blocked · policy: deny
EVERY AI/ML API CALL, ON THE RECORD
01 · USE CASES

What agents do in AI/ML API.

01

Check billing balance

Look up the remaining balance on the account before kicking off a large batch of model calls.

02

Create a chat completion

Send a prompt to a model and get a text response back for use elsewhere in a workflow.

03

Cancel a running job

Stop an in-progress assistant run that's no longer needed, a write action that should be confirmed first.

02 · ACTIONS

30 AI/ML API actions, graded by risk.

Every AI/ML API action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

16

Look things up. Allowed by default.

  • ai_ml_api.get_run
    Get Run
  • ai_ml_api.list_runs
    List Runs
  • ai_ml_api.get_thread
    Get Thread
  • ai_ml_api.get_message
    Get Message
  • ai_ml_api.list_models
    List Models
  • ai_ml_api.get_response
    Get Response by ID
  • ai_ml_api.get_run_step
    Get Run Step
  • ai_ml_api.list_batches
    List Batches
  • ai_ml_api.get_assistant
    Get Assistant
  • ai_ml_api.list_messages
    List Thread Messages
  • ai_ml_api.list_run_steps
    List Run Steps
  • ai_ml_api.list_assistants
    List Assistants
  • ai_ml_api.get_billing_balance
    Get Billing Balance
  • ai_ml_api.get_luma_generation
    Get Luma Generation
  • ai_ml_api.list_luma_generations
    List Luma AI Generations
  • ai_ml_api.list_models_with_details
    List Models With Details

write

10

Create and change things. Allow, or ask the user first.

  • ai_ml_api.create_run
    Create Run
  • ai_ml_api.update_run
    Update Run
  • ai_ml_api.create_thread
    Create Thread
  • ai_ml_api.update_thread
    Update Thread
  • ai_ml_api.create_message
    Create Message
  • ai_ml_api.update_message
    Update Message
  • ai_ml_api.create_assistant
    Create Assistant
  • ai_ml_api.update_assistant
    Update Assistant
  • ai_ml_api.submit_tool_outputs
    Submit Tool Outputs
  • ai_ml_api.text_chat_completion
    Text Chat Completion

destructive

4

Delete, cancel or archive. Ask first, or deny outright.

  • ai_ml_api.cancel_run
    Cancel Run
  • ai_ml_api.delete_thread
    Delete Thread
  • ai_ml_api.delete_message
    Delete Message
  • ai_ml_api.delete_assistant
    Delete Assistant
03 · HOW IT WORKS

AI/ML API in three steps.

  1. 01Your users connect AI/ML APIThey add their AI/ML API api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Run” can wait for the user, and “delete Thread” can be denied outright.
  3. 03Any agent can actYour agent calls AI/ML API through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('ai_ml_api', {
  read: 'allow',
  write: 'ask',        // create_run
  destructive: 'deny',  // delete_thread
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How AI/ML API connects.

Users add their AI/ML API api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same AI/ML API connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use AI/ML API from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actionsAnchor Browser64 actions
ALL AI AND MODELS APPS →
07 · FAQ

AI/ML API and Arc0, answered.

Q01

Can I use AI/ML API with Claude, ChatGPT or Cursor?

Yes. Connect AI/ML API to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the AI/ML API actions you allow.

Q02

How do users connect AI/ML API?

Users add their AI/ML API api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which AI/ML API actions can my agent take?

30 in total: 16 read, 10 write and 4 destructive, such as “create Run”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in AI/ML API?

Yes. Actions like “delete Thread” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call AI/ML API too?

Yes. The same AI/ML API connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug AI/ML API into your agent.

Your users connect AI/ML API once, under your brand. Your agent gets 30 actions behind your policies, with every call on the record.

Connect AI/ML APIBrowse all apps →

Free to build · MCP + REST · Audit log on every plan