Skip to navigation
ModelsMore providers

Provider: Fireworks AI

Call Fireworks AI models through Respan Gateway with unified logs, cost, and latency.
This page is for Respan LLM Gateway users.

Use Respan Gateway to call Fireworks AI models (fireworks_ai/deepseek-v4p1-flash, fireworks_ai/glm-5p3, and fireworks_ai/glm-5p3-flash) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Fireworks AI requires bring your own key (BYOK). Provider usage cannot be paid with Respan credits.

Quick setup

1

Get a Respan API key

Sign up and create a key on the API keys page.

2

Add your Fireworks AI credentials

Configure your Fireworks AI credentials on the Providers page before using the examples below. See Use your own Fireworks AI key.

Send your first request

After configuring your Fireworks AI credentials in Respan, pick the integration that matches your stack. The base URL is https://api.respan.ai/api and your application authenticates with RESPAN_API_KEY.

The Fireworks Python SDK is built on the OpenAI client and accepts a base_url override. Point it at the Respan gateway to keep your existing Fireworks code.

Python
from fireworks.client import Fireworks
client = Fireworks(
    api_key="YOUR_RESPAN_API_KEY",
    base_url="https://api.respan.ai/api",
)
response = client.chat.completions.create(
    model="fireworks_ai/deepseek-v4p1-flash",
    messages=[{"role": "user", "content": "Hello, Fireworks!"}],
)
print(response.choices[0].message.content)

More integrations

Fireworks AI models work with every Respan gateway integration:

Switch models

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

client.chat.completions.create(model="fireworks_ai/deepseek-v4p1-flash", messages=messages)
client.chat.completions.create(model="fireworks_ai/glm-5p3", messages=messages)
client.chat.completions.create(model="fireworks_ai/glm-5p3-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)

Use your own Fireworks AI key (BYOK)

Fireworks AI credentials are required. Configure them in Respan or pass them with each request using one of the options below.

1

Open Providers

Go to the Providers page.

2

Add Fireworks AI

Select Fireworks AI and paste your fireworks.api_key. Grab one from the Fireworks API keys page.

3

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 Fireworks AI key than the default.

{
  "customer_credentials": {
    "fireworks": { "api_key": "YOUR_FIREWORKS_API_KEY" }
  },
  "credential_override": {
    "fireworks_ai/deepseek-v4p1-flash": { "api_key": "ANOTHER_FIREWORKS_API_KEY" }
  }
}

Log without proxying (Optional)

Already calling Fireworks AI 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": "fireworks_ai/deepseek-v4p1-flash",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Fireworks AI through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.