Skip to content
CostPerPrompt

GPT-3.5 Turbo Instruct API Pricing

OpenAI · context window 4K · prices updated 2026-08-02

Input per 1M tokens
$1.50
Output per 1M tokens
$2.00
Cached input per 1M
—

What real workloads cost on GPT-3.5 Turbo Instruct

Workload Per request Per month
1K short requests/day (500 in / 150 out) $0.001 $31.50
Support chatbot, 500 convs/day (~5K in / 1.4K out per conv) $0.0103 $155
Document pipeline, 10K docs/day (3K in / 500 out) $0.0055 $1650

Model your exact traffic in the API cost calculator — it preloads GPT-3.5 Turbo Instruct with caching and batch options.

Cheaper alternatives

Qwen3.6 Plus Alibaba (Qwen) $0.325 in · $1.95 out Qwen3 VL 235B A22B Instruct Alibaba (Qwen) $0.21 in · $1.90 out Qwen3 235B A22B Alibaba (Qwen) $0.455 in · $1.82 out

More OpenAI models

o1-pro GPT-5.5 Pro GPT-5.4 Pro GPT-4

Frequently asked questions

› How much does the GPT-3.5 Turbo Instruct API cost?

GPT-3.5 Turbo Instruct costs $1.50 per million input tokens and $2.00 per million output tokens. In practice, a typical short request (500 tokens in, 150 out) costs about $0.001.

› What does 1,000 requests per day cost on GPT-3.5 Turbo Instruct?

At 500 input + 150 output tokens per request, 1,000 requests/day costs about $31.50 per month. Heavier workloads scale linearly — use our API cost calculator to model your exact traffic.

› How can I reduce GPT-3.5 Turbo Instruct costs?

Three levers, in order of impact: (1) route routine requests to a cheaper tier and keep GPT-3.5 Turbo Instruct for hard cases; (2) enable prompt caching, which typically halves chatbot bills; (3) use the batch API for non-urgent jobs at a ~50% discount.

› Is GPT-3.5 Turbo Instruct worth the price?

It depends on task difficulty. Flagship models earn their premium on complex reasoning, coding, and high-stakes output; mini/flash tiers handle classification, extraction and routine chat at 10–30× lower cost. Benchmark a sample of your real workload on both before committing.