Quickstart

Connect a coding harness, application, or LLM gateway to Fireworks and make your first Nexus request.

Pick how you work. Each path takes a few minutes and uses the same Fireworks models, routers, and account controls.

Coding harness

Claude Code, Codex, OpenCode, Cursor IDE, and more

API or SDK

OpenAI, Anthropic, or Fireworks SDK

LLM gateway

LiteLLM, Portkey, and other gateways

You need a Fireworks API key for the API and gateway paths. FireConnect can create one for you when you sign in.

Connect a coding harness

1. Install FireConnect

   curl -fsSL https://fireconnect.fireworks.ai/install.sh | bash
   

   Requires Node.js 18 or later. On Windows, run it from Git Bash.

2. Sign in

   fireconnect login
   

   Sign in with your browser, or paste an existing Fireworks key.

3. Connect your harness

   Claude Code

   fireconnect claude
   

   The Codex CLI, the Codex app, and the ChatGPT desktop app share one config, so fireconnect codex connects all three. For desktop apps, including Cursor IDE and VS Code, quit the app first. See Coding Harnesses for every harness.

4. Restart and pick a model

   Restart the harness and open its model picker. You will see auto, FireRouter, and Fireworks open models.

   

   Fireworks models and routers in the Claude Code model picker

   fireconnect claude status shows the configured model and Fireworks endpoint.

Prefer not to install anything? Every harness has a Manual setup tab in Coding Harnesses with the exact settings to add yourself.

Call the API

1. Export your key

   export FIREWORKS_API_KEY="fw_..."
   
2. Send a request

   Point the SDK you already use at Fireworks:

   cURL

   curl https://api.fireworks.ai/inference/v1/chat/completions \
     -H "Authorization: Bearer $FIREWORKS_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "glm-latest",
       "messages": [{"role": "user", "content": "Say pong in one word."}]
     }'
   

   The reply says pong.
3. Try a router

   Change model to firerouter/opus. FireRouter picks a model for each turn, and the response model field shows which one served it. Routes with closed models need a provider credential.

   More examples, including the Responses API: FireRouter Setup.

Use an LLM gateway

1. Add a Fireworks model to LiteLLM

   config.yaml

   model_list:
     - model_name: glm-latest
       litellm_params:
         model: fireworks_ai/accounts/fireworks/routers/glm-latest
         api_key: os.environ/FIREWORKS_API_KEY
         api_base: https://api.fireworks.ai/inference/v1
   
2. Start the proxy

   pip install "litellm[proxy]"
   litellm --config config.yaml
   
3. Send a request

   curl http://localhost:4000/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
       "model": "glm-latest",
       "messages": [{"role": "user", "content": "Say pong in one word."}]
     }'
   

   The reply says pong.

Using Portkey, or adding FireRouter to your gateway? See FireRouter Setup and LLM Gateways.

Next steps

Open Models

Use auto, follow a model family, choose a fast tier, or pin a version.

FireRouter

Let one model ID choose a model for each new user turn.

Usage and Cost

See session estimates and Fireworks model usage by model, user, or API key.

Spend Limits

Set per-user caps for supported Fireworks serverless models.