GPT-4o (2024-05-13) pricing and routing profile
GPT-4o (2024-05-13) from OpenAI lists at $5.00 per million input tokens and $15.00 per million output tokens, with a 128,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool callingStructured outputLog probabilities
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $3.15 |
| Chat reply (2,000 in, 400 out) | $16.00 |
| Retrieval-augmented answer (8,000 in, 500 out) | $47.50 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Yes. At least one host return token log probabilities for GPT-4o (2024-05-13), which is the confidence signal Gimbix uses to let a cheaper model answer first.
Cheaper models that can answer first
Models priced below GPT-4o (2024-05-13) that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| Qwen3.8 Max Prime | $4.00 / $12.00 | 20% |
| Ember-1 | $3.00 / $15.00 | 25% |
| Kimi K3 | $3.00 / $15.00 | 25% |
| GLM 5.3 Prime | $2.80 / $8.80 | 43% |
| GPT Audio | $2.50 / $10.00 | 44% |
| GPT-4o (2024-11-20) | $2.50 / $10.00 | 44% |
Questions
How much does GPT-4o (2024-05-13) cost?
GPT-4o (2024-05-13) lists at $5.00 per million input tokens and $15.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $16.00 per 1,000 requests.
What is the context window of GPT-4o (2024-05-13)?
128,000 tokens.
Can a cheaper model replace GPT-4o (2024-05-13)?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-4o (2024-05-13) on one half of your requests and make at most three answers worse on the other.