Connect → OpenAI SDK and curl

Use AxForge with the OpenAI SDK and curl

The official OpenAI SDKs take a base URL. Set it to https://api.axforge.ai/v1, use your AxForge key, and the rest of your code stays as it is: chat, streaming, tools, embeddings.

The first call

1. Python

   pip install openai

   import os
   from openai import OpenAI
   
   client = OpenAI(base_url="https://api.axforge.ai/v1", api_key=os.environ["AXFORGE_API_KEY"])
   
   reply = client.chat.completions.create(
       model="qwen3.8-27b",
       messages=[{"role": "user", "content": "Say hello in five words"}],
   )
   print(reply.choices[0].message.content)

   

2. Node

   npm install openai

   import OpenAI from "openai";
   
   const client = new OpenAI({ baseURL: "https://api.axforge.ai/v1", apiKey: process.env.AXFORGE_API_KEY });
   
   const reply = await client.chat.completions.create({
     model: "qwen3.8-27b",
     messages: [{ role: "user", content: "Say hello in five words" }],
   });
   console.log(reply.choices[0].message.content);

   

3. curl

   No SDK at all: the same call as plain HTTP.

   curl https://api.axforge.ai/v1/chat/completions \
     -H "Authorization: Bearer $AXFORGE_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{"model":"qwen3.8-27b","messages":[{"role":"user","content":"Say hello in five words"}]}'

   The reply names the model that answered and the tokens it used:

   

Streaming

The words arrive as they are written:

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.axforge.ai/v1", api_key=os.environ["AXFORGE_API_KEY"])

stream = client.chat.completions.create(
    model="qwen3.8-27b", stream=True,
    messages=[{"role": "user", "content": "Count to five"}],
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="", flush=True)
print()

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.axforge.ai/v1", apiKey: process.env.AXFORGE_API_KEY });

const stream = await client.chat.completions.create({
  model: "qwen3.8-27b", stream: true,
  messages: [{ role: "user", content: "Count to five" }],
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
console.log();

Embeddings

e = client.embeddings.create(model="embeddings", input="a sentence to embed")
print(len(e.data[0].embedding))   # 1024

More on Embeddings.

The Responses API

AxForge also serves OpenAI's newer Responses API, so client.responses.create works with the same client:

r = client.responses.create(model="qwen3.8-27b", input="Say hello in five words")
print(r.output_text)

The settings

Which model for what: qwen3.8-27b is the everyday default and reads images, glm-5.3-flash thinks before it answers, mimo-v2.6-flash is the fastest. Every model id is on Models, and client.models.list() returns them too.

Check that it works

reply.model is the AxForge model you asked for and reply.usage has token counts. The call shows in the console under API Keys → Recent calls within a minute.

When it does not work

Not sure which it is? The connection doctor makes seven small checks on your key and names the fix: irm https://dev.axforge.ai/assets/axforge-doctor.ps1 | iex in PowerShell, curl -fsSL https://dev.axforge.ai/assets/axforge-doctor.sh | bash on macOS and Linux.

Test a call says in one click whether a problem is your key, your balance or us.