Provider: Inference.net

Call Inference.net models through Respan Gateway with unified logs, cost, and latency.

This page is for Respan LLM Gateway users.

Use Respan Gateway to call Inference.net models while keeping unified observability (logs, cost, latency, reliability) in Respan.

Paste this into your coding agent:


Help me set up the Respan gateway to call Inference.net models.
Follow https://www.respan.ai/docs/integrations/gateway/model-providers/inference.md

Quick setup

Add credits (recommended)

Top up credits to pay through Respan. No Inference.net key required, Respan handles provider auth and billing.

Prefer to route through your own Inference.net account? See Use your own Inference.net key.

Send your first request

Pick the integration that matches your stack. The base URL is https://api.respan.ai/api and the only key needed is your RESPAN_API_KEY.

Inference.net is OpenAI-compatible. Point the OpenAI SDK at the Respan gateway and call any Inference.net model.


from openai import OpenAI

client = OpenAI(
    api_key="YOUR_RESPAN_API_KEY",
    base_url="https://api.respan.ai/api",
)

response = client.chat.completions.create(
    model="inference_net/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Hello, Inference.net!"}],
)
print(response.choices[0].message.content)

Call respan.chat(...) explicitly to use the Gateway Chat Completions endpoint.

Use @ai-sdk/openai and point createOpenAI at the Respan gateway.


import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const respan = createOpenAI({
  apiKey: process.env.RESPAN_API_KEY!,
  baseURL: "https://api.respan.ai/api",
});

const result = await generateText({
  model: respan.chat("inference_net/deepseek-v4.1-flash"),
  prompt: "Hello, Inference.net!",
});
console.log(result.text);

Call the Respan REST API directly from any language.


import requests

response = requests.post(
    "https://api.respan.ai/api/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "inference_net/deepseek-v4.1-flash",
        "messages": [{"role": "user", "content": "Hello, Inference.net!"}],
    },
)
print(response.json()["choices"][0]["message"]["content"])

More integrations

Inference.net models work with every Respan gateway integration:

Switch models

Change the model parameter to call any supported model through the same client. Use the inference_net/ prefix to disambiguate when routing across providers. Browse the full list on the Models page .


client.chat.completions.create(model="inference_net/deepseek-v4.1-flash", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)
client.chat.completions.create(model="gemini/gemini-3.8-flash", messages=messages)

Use your own Inference.net key (BYOK)

Credits are the default path. If you’d rather bill Inference.net directly, attach your own provider key.

Open Providers

Go to the Providers page .

Add Inference.net

Select Inference.net and paste your inference_net.api_key.

Load balancing (Optional)

Add multiple credential sets and use Load balancing weight to distribute traffic across them.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Inference.net key than the default.


{
  "customer_credentials": {
    "inference_net": { "api_key": "YOUR_INFERENCE_NET_API_KEY" }
  },
  "credential_override": {
    "inference_net/deepseek-v4.1-flash": { "api_key": "ANOTHER_INFERENCE_NET_API_KEY" }
  }
}

Log without proxying (Optional)

Already calling Inference.net directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.


import requests

requests.post(
    "https://api.respan.ai/api/request-logs/create/",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "inference_net/deepseek-v4.1-flash",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Inference.net through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.