GPT-3.5 Turbo

OpenAI's lightweight model of the GPT-3.5 generation.

Context: 16K tokens
Max output: 4K
Cutoff: Sep 2021
Released: Mar 2023

Visit OpenAI Compare vs other LLMs →

Hosted API price

List price via OpenAI · per 1M tokens

USD

Input: $0.50 /1M
Output: $1.50 /1M
Hosted by: 2 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving GPT-3.5 Turbo, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving GPT-3.5 Turbo, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
OpenAI Creator	$0.50	$1.50	$8.00	Visit website
Azure	$0.50	$1.50	$8.00	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Similarly priced models

The models nearest GPT-3.5 Turbo by blended rate, each at its own cheapest provider.

Models priced nearest GPT-3.5 Turbo per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs GPT-3.5 Turbo
Qwen3-235B-A22B Thinking (2507) Alibaba Cloud	$0.575	$0.23	$2.30	262K		−14%
Qwen3-Coder-480B-A35B Alibaba Cloud	$0.575	$0.38	$1.55	262K		−14%
GPT-4.1 Mini OpenAI	$0.60	$0.40	$1.60	1M	Jun 2024	−10%
Gemini 2.5 Flash Google Cloud	$0.6667	$0.30	$2.50	1M	Jan 2025	0%
Gemini 3.5 Flash-Lite Google Cloud	$0.6667	$0.30	$2.50	1M	Mar 2026	0%
GPT-3.5 Turbo This model OpenAI	$0.6667	$0.50	$1.50	16K	Sep 2021
Mistral Large 3 Mistral	$0.6667	$0.50	$1.50	256K		0%
Qwen3.5-Plus Alibaba Cloud	$0.7333	$0.40	$2.40	1M		+10%
GLM-5 Z.AI	$0.7667	$0.60	$1.60	200K		+15%
DeepSeek R1 Distill Llama 70B DeepSeek	$0.80	$0.80	$0.80	131K		+20%
GLM-4.7 Z.AI	$0.8667	$0.60	$2.20	205K		+30%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Thunder Compute

RTX A6000 from $0.35, A100 from $1.09, per GPU per hour

Billed per minute, no commitment, no minimums

One click into VS Code or Cursor, no SSH setup

See live pricing

Capabilities

What GPT-3.5 Turbo accepts and can do, as published by OpenAI.

Text Accepts and generates natural-language text.

Common questions

What is GPT-3.5 Turbo good for?

Cheap text-only chat and classification. OpenAI calls it a legacy model and has recommended GPT-4o Mini instead since July 2024.

When is GPT-3.5 Turbo not a good fit?

Images, tool calling and structured output, since it has none of them. Its knowledge is years out of date, and OpenAI plans to shut down the API model in October 2026.

What is the cheapest way to run GPT-3.5 Turbo?

The cheapest hosted rate is $0.50 / $1.50 per 1M tokens via OpenAI.

How does GPT-3.5 Turbo compare with GPT-4o Mini?

OpenAI recommends GPT-4o Mini in place of GPT-3.5 Turbo and says it is smarter, cheaper and just as fast, with better long-context performance, and can be fine-tuned or distilled from GPT-4o. GPT-3.5 Turbo lists at 233% more per 1M input tokens and 150% more per 1M output tokens than GPT-4o Mini. It came out 16 months earlier, has an older knowledge cutoff (September 2021 against October 2023), a smaller context (16K against 128K tokens) and a smaller max output (4K against 16K tokens) and takes no image input, which GPT-4o Mini does.

Can I self-host GPT-3.5 Turbo?

No. OpenAI does not publish the weights; GPT-3.5 Turbo is available only through hosted APIs.