Quickstart

Start integrating LLM APIs through JBridge in minutes — single endpoint, multiple models, pay per token.

JBridge gives you a single API gateway to multiple LLM providers (OpenAI, Anthropic, DeepSeek, and more). One key, one base URL, transparent pricing.

1. Get an API key

Sign in to your dashboard and create a new key from the API Keys page. Keys look like sk-jb-YOUR_KEY and are shown only once at creation — store them securely.

2. Base URL

https://jbridge.ai

All endpoints below are relative to this base URL.

JBridge exposes the following proxy endpoints. "Inference" endpoints deduct credit based on usage; "Utility" endpoints list available models and estimate token counts — they are free and never deduct credit, so you can estimate cost before topping up.

Method	Endpoint	Category	Compatible with / Purpose
`POST`	`/api/v1/chat/completions`	Inference	OpenAI SDK
`POST`	`/api/v1/responses`	Inference	OpenAI Responses API / Codex CLI
`POST`	`/api/v1/messages`	Inference	Anthropic SDK / Claude Code
`GET`	`/api/v1/models`	Utility	List available models (free)
`POST`	`/api/v1/messages/count_tokens`	Utility	Anthropic token estimation (free)
`POST`	`/api/v1/responses/input_tokens`	Utility	OpenAI Responses token estimation (free)

4. First request

curl

curl https://jbridge.ai/api/v1/chat/completions \
  -H "Authorization: Bearer sk-jb-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python (OpenAI SDK)

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Claude Code

export ANTHROPIC_BASE_URL=https://jbridge.ai/api
export ANTHROPIC_AUTH_TOKEN=sk-jb-YOUR_KEY

Reads ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN from your shell environment. Add to ~/.zshrc or ~/.bashrc to persist. See the official Claude Code LLM gateway docs.

Codex CLI

# ~/.codex/config.toml
openai_base_url = "https://jbridge.ai/api/v1"

export OPENAI_API_KEY=sk-jb-YOUR_KEY

openai_base_url lives in ~/.codex/config.toml; OPENAI_API_KEY is read from the shell. See the official Codex config docs.

What's next?

See the full model catalogue and pricing
Configure other tools: Cursor, Windsurf, OpenAI / Anthropic SDKs
Common errors and policies in the FAQ

Available Models