GPT-4.1 pricing and routing profile
GPT-4.1 from OpenAI lists at $2.00 per million input tokens and $8.00 per million output tokens, with a 1,047,576-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool callingStructured output
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $1.28 |
| Chat reply (2,000 in, 400 out) | $7.20 |
| Retrieval-augmented answer (8,000 in, 500 out) | $20.00 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Not as a first-answer model through OpenRouter: no host returns token log probabilities for GPT-4.1. It can still be the model Gimbix falls back to when a cheaper model is unsure.
Cheaper models that can answer first
Models priced below GPT-4.1 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 |
|---|---|---|
| Grok 4.7 | $1.60 / $4.80 | 29% |
| Qwen3.7 Max | $1.48 / $4.42 | 34% |
| GLM 5.1 | $1.40 / $4.40 | 37% |
| Qwen3.6 Max Preview | $1.03 / $6.16 | 37% |
| Grok 4.3 | $1.25 / $2.50 | 51% |
| Grok 4.20 Multi-Agent | $1.25 / $2.50 | 51% |
Questions
How much does GPT-4.1 cost?
GPT-4.1 lists at $2.00 per million input tokens and $8.00 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 $7.20 per 1,000 requests.
What is the context window of GPT-4.1?
1,047,576 tokens.
Can a cheaper model replace GPT-4.1?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-4.1 on one half of your requests and make at most three answers worse on the other.