GPT-3.5 Turbo Instruct pricing and routing profile
GPT-3.5 Turbo Instruct from OpenAI lists at $1.50 per million input tokens and $2.00 per million output tokens, with a 4,095-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Structured outputLog probabilities
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.92 |
| Chat reply (2,000 in, 400 out) | $3.80 |
| Retrieval-augmented answer (8,000 in, 500 out) | $13.00 |
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 Instruct, 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 Instruct 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 Build 0.1 | $1.00 / $2.00 | 26% |
| GPT-3.5 Turbo (older v0613) | $1.00 / $2.00 | 26% |
| DeepSeek V4 Pro 0423 | $0.955 / $1.91 | 30% |
| Morph V3 Large | $0.90 / $1.90 | 33% |
| Qwen2.5 VL 72B Instruct | $0.80 / $1.00 | 47% |
| GLM 5 | $0.60 / $1.92 | 48% |
Questions
How much does GPT-3.5 Turbo Instruct cost?
GPT-3.5 Turbo Instruct lists at $1.50 per million input tokens and $2.00 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 $3.80 per 1,000 requests.
What is the context window of GPT-3.5 Turbo Instruct?
4,095 tokens.
Can a cheaper model replace GPT-3.5 Turbo Instruct?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-3.5 Turbo Instruct on one half of your requests and make at most three answers worse on the other.