GPT-3.5 Turbo pricing and routing profile
GPT-3.5 Turbo from OpenAI lists at $0.50 per million input tokens and $1.50 per million output tokens, with a 16,385-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) | $0.315 |
| Chat reply (2,000 in, 400 out) | $1.60 |
| Retrieval-augmented answer (8,000 in, 500 out) | $4.75 |
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-3.5 Turbo, which is the confidence signal Gimbix uses to let a cheaper model answer first.
Cheaper models that can answer first
Models priced below GPT-3.5 Turbo 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 |
|---|---|---|
| DeepSeek V4 Flash Vision Exp | $0.44 / $1.32 | 12% |
| MiMo-V2.5-Pro | $0.435 / $0.87 | 24% |
| Qwen3.7 Plus | $0.32 / $1.28 | 28% |
| GLM 5.3 | $0.33 / $1.20 | 29% |
| Muse Glimmer 30B | $0.30 / $1.20 | 32% |
| MiniMax M3 | $0.30 / $1.20 | 32% |
Questions
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo lists at $0.50 per million input tokens and $1.50 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 $1.60 per 1,000 requests.
What is the context window of GPT-3.5 Turbo?
16,385 tokens.
Can a cheaper model replace GPT-3.5 Turbo?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-3.5 Turbo on one half of your requests and make at most three answers worse on the other.