OpenAI

OpenAI is one of the most widely used AI providers. TokenSense routes OpenAI chat, Responses, embeddings, image, and file-audio requests. Current GPT options include GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna. Model access depends on your OpenAI account; a catalog listing does not grant upstream access.

Connect OpenAI to TokenSense

Already have a TokenSense account? Here's how to start tracking OpenAI costs:

Step 1: Go to your dashboard → Provider Keys → Add your OpenAI API key. TokenSense stores it securely and uses it to forward requests to OpenAI on your behalf.

Step 2: In your workflow tool (n8n, Make, or your custom code), change the API base URL from https://api.openai.com/v1 to your TokenSense endpoint. Your TokenSense endpoint is shown on your dashboard home page.

Step 3:Use your TokenSense API key as the auth header (instead of your OpenAI key directly). That's it — requests flow through TokenSense and costs appear in your dashboard within seconds.

Using n8n? The TokenSense n8n node handles all of this automatically — no URL swapping needed. Install the community node and add your TokenSense credential.

Supported chat models

All pricing is per 1 million tokens (USD).

ModelInput (per 1M tokens)Output (per 1M tokens)
gpt-6.1-sol$2.00$10.00
gpt-6-astra$10.00$50.00
gpt-6-sol$2.00$10.00
gpt-6-luna$0.10$0.50
gpt-4.1-mini$0.40$1.60

Reasoning and tool compatibility

GPT-6.1 Sol supports low, medium, high, xhigh, and max effort. Use /v1/responses for its tool requests; Chat Completions is supported without tools. GPT-6 Astra also requires Responses for tools. TokenSense returns an actionable error before booking request quota when a Chat request uses an unsupported tool path.

For GPT-6.1 Sol, input and cached-input rates double and the output rate increases by 50% above 272,000 input tokens. Batch, service tiers, and regional processing can change the final rate. See OpenAI's model guide and pricing.

Image and audio billing coverage

GPT Image models use separate text and image token rates. A fixed per-image estimate does not represent their exact bill. GPT Image 2 and 2.5 use returned modality token counts; GPT Transcribe uses returned billable seconds. Missing or unsupported usage remains an unknown cost. Mini TTS returns binary audio without billable token counts, so TokenSense explicitly marks its pricing unavailable. Realtime audio is outside the implemented file-audio paths.

Embedding models

ModelCost (per 1M tokens)Notes
text-embedding-3-small$0.02Recommended for most use cases
text-embedding-3-large$0.13Higher dimension, better retrieval
text-embedding-ada-002$0.10Legacy

Using OpenAI in your workflows

TokenSense works with any tool that can make HTTP requests to an OpenAI-compatible endpoint:

n8n: Install the TokenSense community node. It handles authentication and endpoint routing automatically.

Make / Zapier: Use an HTTP module pointed at your TokenSense endpoint with your TokenSense API key as the Bearer token. See the Make & Zapier guide.

Custom code / cURL: Replace https://api.openai.com/v1 with your TokenSense endpoint URL. See the API reference.

Related