API Documentation - IteraCompute

1. Overview

The IteraCompute API is OpenAI-compatible: if your application already talks to the OpenAI API, migrating is a change of base_url and API key. Chat completions, streaming and tool calling work the way you expect.

2. Base URL & Authentication

All requests go to https://api.iteracompute.com/v1 and authenticate with your API key in the Authorization header.

curl https://api.iteracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "iteracompute/qwen3.8-27b", "messages": [{"role": "user", "content": "Hello!"}]}'

3. Model IDs

Model IDs use the format iteracompute/<model>. List the models available to your key at any time:

curl https://api.iteracompute.com/v1/models \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY"

A key only returns the models it is scoped to. The current lineup is on the model page; final availability is confirmed per agreement.

4. Chat Completions

POST /v1/chat/completions follows the OpenAI request and response format:

from openai import OpenAI

client = OpenAI(base_url="https://api.iteracompute.com/v1",
                api_key="$ITERACOMPUTE_API_KEY")

resp = client.chat.completions.create(
    model="iteracompute/qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello!"}])

print(resp.choices[0].message.content)
print(resp.usage)  # prompt_tokens / completion_tokens / total_tokens

5. Streaming (SSE)

Set "stream": true to receive server-sent events. Chunks arrive as generated; token usage is included in the final chunk that carries usage, before the terminal [DONE] event. Treat the stream as one logical request: once tokens have been emitted, the request is not retried transparently.

stream = client.chat.completions.create(
    model="iteracompute/qwen3.8-27b",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
    stream_options={"include_usage": True})

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
    if chunk.usage:  # final chunk: token usage
        print("\n", chunk.usage)

6. Tool Calling

Tools are declared in the tools parameter, following the OpenAI function-calling format. When the model decides to call a tool, the response contains tool_calls; send tool results back with role "tool" to continue the conversation.

resp = client.chat.completions.create(
    model="iteracompute/qwen3.8-27b",
    messages=[{"role": "user", "content": "What is the weather in Singapore?"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a city",
            "parameters": {
                "type": "object",
                "properties": {"city": {"type": "string"}},
                "required": ["city"],
            },
        },
    }])

tool_calls = resp.choices[0].message.tool_calls  # execute & reply with role "tool"

7. Error Codes

Errors use the OpenAI error format with a JSON body of {"error": {"message", "type", "code"}}:

Status	Meaning
400	Invalid request - malformed JSON or missing required parameters
401	Authentication failed - missing or invalid API key
403	Key not permitted for this model or action
404	Unknown model or endpoint
429	Rate limit exceeded - slow down and honor Retry-After
500	Internal error - safe to retry the request
503	Model temporarily unavailable - retry with backoff

8. Rate Limits

Every key carries its own limits - requests per minute, tokens per minute and concurrent streams. When a limit is reached the API returns 429 promptly rather than queueing the request; honor the Retry-After header before retrying. Your key's limits are communicated during onboarding and can be adjusted per agreement.

9. Support

Integration questions: support@iteracompute.com