Provider Keys

Overview

To use TokenRouter, you need to provide API keys for the AI providers you want to use. TokenRouter supports two methods:

1. Console Configuration (Recommended) - Store encrypted keys in the console
2. Inline Headers - Pass keys directly in requests

Supported Providers

Provider	Models	Get API Key
OpenAI	GPT-4o, GPT-4 Turbo	platform.openai.com
Anthropic	Claude 3.7 Sonnet, Opus, Haiku	console.anthropic.com
Google	Gemini 1.5 Pro, Flash	makersuite.google.com
Mistral	Mistral Large, Medium	console.mistral.ai
DeepSeek	DeepSeek V3	platform.deepseek.com
Meta	Llama 4	llama.meta.com (special access)

Adding Provider Keys in Console

1. Go to Console → Providers
2. Click Add Provider
3. Select provider (OpenAI, Anthropic, etc.)
4. Paste your API key
5. Click Save

Keys are encrypted and never exposed in logs.

Inline Provider Keys

Pass provider keys directly in request headers:

TypeScript

const response = await client.responses.create({
  model: 'gpt-4o',
  input: 'Hello!'
}, {
  headers: {
    'X-OpenAI-Key': process.env.OPENAI_API_KEY
  }
});

Python

response = client.responses.create(
    model="gpt-4o",
    input="Hello!",
    extra_headers={
        "X-OpenAI-Key": os.getenv("OPENAI_API_KEY")
    }
)

cURL

curl https://api.tokenrouter.io/v1/responses \
  -H "Authorization: Bearer tr_..." \
  -H "X-OpenAI-Key: sk-proj-..." \
  -d '{"model": "gpt-4o", "input": "Hello!"}'

Supported Headers

• X-OpenAI-Key - OpenAI
• X-Anthropic-Key - Anthropic
• X-Gemini-Key - Google Gemini
• X-Mistral-Key - Mistral
• X-DeepSeek-Key - DeepSeek

Next Steps

• Auto Routing
• Standard Requests