Home / Models / OpenAI / GPT-3.5 Turbo 16k

GPT-3.5 Turbo 16k pricing and routing profile

GPT-3.5 Turbo 16k from OpenAI lists at $3.00 per million input tokens and $4.00 per million output tokens, with a 16,385-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$3.00
Output, per 1M tokens$4.00
Context window16K
Confidence signalAvailable

Tool callingStructured outputLog probabilities

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$1.84
Chat reply (2,000 in, 400 out)$7.60
Retrieval-augmented answer (8,000 in, 500 out)$26.00

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 16k, 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 16k that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
GPT-5 Image Mini$2.50 / $2.0024%
Grok 4.3$1.25 / $2.5054%
Grok 4.20 Multi-Agent$1.25 / $2.5054%
Grok 4.20$1.25 / $2.5054%
Qwen3 Max Thinking$0.78 / $3.9059%
Qwen3 Max$0.78 / $3.9059%

Questions

How much does GPT-3.5 Turbo 16k cost?

GPT-3.5 Turbo 16k lists at $3.00 per million input tokens and $4.00 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 $7.60 per 1,000 requests.

What is the context window of GPT-3.5 Turbo 16k?

16,385 tokens.

Can a cheaper model replace GPT-3.5 Turbo 16k?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-3.5 Turbo 16k on one half of your requests and make at most three answers worse on the other.