OpenAI compatibility

Mindforge implements the standard OpenAI API, so you can use any OpenAI-compatible SDK or tool.

Setup

Point any OpenAI SDK at https://api.mindforge.ai/v1 and use your Mindforge API key.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mindforge.ai/v1",
    api_key="sk-mf-YOUR_KEY",
)

# Non-streaming
response = client.chat.completions.create(
    model="pearl-1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)
print(response.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="pearl-1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.mindforge.ai/v1",
  apiKey: "sk-mf-YOUR_KEY",
});

// Non-streaming
const response = await client.chat.completions.create({
  model: "pearl-1",
  messages: [
    { role: "user", content: "Hello!" },
  ],
});
console.log(response.choices[0].message.content);

// Streaming
const stream = await client.chat.completions.create({
  model: "pearl-1",
  messages: [
    { role: "user", content: "Hello!" },
  ],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Supported endpoints

Endpoint	Description
POST /v1/chat/completions	Chat completions (streaming + non-streaming)
GET /v1/models	List available models
GET /v1/models/{model}	Get model details

Supported features

Feature	Supported
Streaming (SSE)	Yes
Non-streaming	Yes
Tool/function calling	Yes
Multi-turn conversations	Yes
System messages	Yes
temperature, max_tokens, top_p, stop	Yes
frequency_penalty, presence_penalty	Yes
response_format (JSON mode)	Yes
seed	Yes
n (multiple choices)	Yes

Listing available models

curl https://api.mindforge.ai/v1/models \
  -H "Authorization: Bearer $MINDFORGE_API_KEY"

Returns models in the standard OpenAI format:

{
  "object": "list",
  "data": [
    {
      "id": "pearl-1",
      "object": "model",
      "created": 1714000000,
      "owned_by": "vllm"
    }
  ]
}