Chat Models

AI models for chat, Q&A, reasoning, and text generation

Chat · OpenAI

gpt-4o
Available
JSON modePrompt CacheTool useVisionCached input 50% less
TokenLab price-15% Discount
Input$2.13Output$8.50/1M
Official price
Input$2.50Output$10.00/1M
gpt-4o-mini
Available
JSON modePrompt CacheTool useVisionCached input 50% less
TokenLab price-15% Discount
Input$0.1275Output$0.51/1M
Official price
Input$0.15Output$0.60/1M
gpt-5-pro
Available
JSON modeReasoningTool useVision
TokenLab price/ Official price— Discount
—
gpt-oss-20b
Available
JSON modeTool use
TokenLab price/ Official price— Discount
—
gpt-audio-1.5
Available
Tool use
TokenLab price— Discount
—
Official price
Input$2.50Output$10.00/1M
2 / 2

All model series

6 series

Choosing the right chat model

The right model balances task fit, output quality, latency, and price.

Selection signals

  • Match the model to the input and output you actually need.
  • Compare models that use the same pricing unit.
  • A small test reveals quality and latency differences that a catalog cannot.

FAQ

What makes a good chat model?

A strong fit matches the task, quality bar, latency target, and budget. A small evaluation set makes quality and reliability differences easier to see.

Can I switch models later?

Yes. Keep the public model ID and request format explicit, and compare alternatives on the same tasks.