Documentation Index
Fetch the complete documentation index at: https://docs.orgo.ai/llms.txt
Use this file to discover all available pages before exploring further.
Tell an Orgo computer what to do in plain English. The AI sees the screen, clicks, types, and runs commands until the task is done. Uses the standard OpenAI SDK — no new libraries to learn.
from openai import OpenAI
from orgo import Computer
computer = Computer()
client = OpenAI(
base_url="https://api.orgo.ai/api/v1",
api_key="sk_live_..." # Your Orgo API key
)
response = client.chat.completions.create(
model="claude-sonnet-4.6",
messages=[{"role": "user", "content": "Open Chrome and search for AI news"}],
extra_body={"computer_id": computer.computer_id},
)
print(response.choices[0].message.content)
Streaming
stream = client.chat.completions.create(
model="claude-sonnet-4.6",
messages=[{"role": "user", "content": "Open Chrome and search for AI news"}],
extra_body={"computer_id": computer.computer_id},
stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
Multi-turn
Pass thread_id from a previous response to continue where you left off:
response = client.chat.completions.create(
model="claude-sonnet-4.6",
messages=[{"role": "user", "content": "Open Chrome and go to github.com"}],
extra_body={"computer_id": computer.computer_id},
)
thread_id = response.orgo["thread_id"]
# The AI remembers it already opened Firefox
response2 = client.chat.completions.create(
model="claude-sonnet-4.6",
messages=[{"role": "user", "content": "Search for 'orgo'"}],
extra_body={"computer_id": computer.computer_id, "thread_id": thread_id},
)
Bring your own key
Use your own Anthropic API key — no Orgo credits consumed:
curl https://api.orgo.ai/api/v1/chat/completions \
-H "Authorization: Bearer sk_live_..." \
-H "X-Anthropic-Key: sk-ant-..." \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-4.6","computer_id":"...","messages":[{"role":"user","content":"Open Chrome"}]}'
Reference
Endpoint
POST https://api.orgo.ai/api/v1/chat/completions
Authorization: Bearer sk_live_...
Request body
| Field | Type | Required | Description |
|---|
model | string | No | claude-sonnet-4.6 (default) or claude-opus-4.6 |
messages | array | Yes | [{role, content}] — same format as OpenAI |
computer_id | string | Yes | ID of a running Orgo computer |
stream | boolean | No | Stream response as SSE (default: false) |
thread_id | string | No | Continue a previous session |
max_steps | number | No | Max agent steps (default: 100) |
Response
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "claude-sonnet-4.6",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "Done. Firefox is open with AI news search results."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 1200,
"completion_tokens": 340,
"total_tokens": 1540
},
"orgo": {
"thread_id": "thr_abc123",
"steps": 8
}
}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant"},"index":0,"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"delta":{"content":"Opening Firefox..."},"index":0,"finish_reason":null}]}
data: [DONE]
Models
| Model | Description |
|---|
claude-sonnet-4.6 | Fast, cost-effective (default) |
claude-opus-4.6 | Most capable, best for complex tasks |
Errors
| Status | Code | Meaning |
|---|
| 401 | invalid_api_key | Invalid or missing API key |
| 402 | credits_exhausted | Add credits at orgo.ai/settings/billing |
| 400 | missing_computer_id | computer_id is required |
| 400 | invalid_model | Use claude-sonnet-4.6 or claude-opus-4.6 |
| 404 | computer_not_found | Computer not found or you don’t have access |
