OpenAI

GPT 3.5 Turbo API Pricing 2026

Compare pricing, benchmarks, and providers for GPT 3.5 Turbo. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

GPT 3.5 Turbo was released on May 28, 2023. Pricing starts at $0.500 per million input tokens and $1.00 per million output tokens. The model supports a context window of up to 16K tokens. API access is available through OpenAI.

Context Window
16K
tokens
Pricing
Input$0.500
Output$1.00
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Tools

GPT 3.5 Turbo is priced at $0.500 per million input tokens and $1.00 per million output tokens. It has a context window of 16,385 tokens. It is available from 3 providers, with Vercel the cheapest at $0.500 per million input tokens (input prices range from $0.500 to $1.50). On benchmarks, GPT 3.5 Turbo scores Aider 57.9 (43rd percentile).

Pricing Comparison

Compare GPT 3.5 Turbo with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.500
$1.000
—
—
—
16,385
Try
$0.500
$0.800
—
—
—
32,768
Try
$0.500
$3.000
—
—
—
1,048,576
Try
$0.500
$1.500
—
—
—
262,144
Try
$0.500
$0.700
—
—
—
256,000
Try
$0.500
$0.500
—
—
—
32,768
Try
$0.500
$2.150
—
—
—
163,840
Try
$0.500
$0.500
—
—
—
32,768
Try
$0.500
$2.500
—
—
—
-
Try
$0.500
$0.900
—
—
—
131,072
Try
$0.500
$1.500
—
—
—
128,000
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

GPT 3.5 Turbo is available from multiple providers with different pricing and availability.

3
Providers
$0.500
Cheapest Input/M
$1.000
Cheapest Output/M
Vercel
Best Price

Provider Pricing

3 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
V
Vercel
Best Price
$0.500
$1.500
-
-
-
$0.750
$1.000
-
-
-
OpenAI
OpenAI
$1.500
$2.000
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does GPT 3.5 Turbo perform? Vote based on your experience.

Cost vs. Quality

Compare GPT 3.5 Turbo's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try GPT 3.5 Turbo

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test GPT 3.5 Turbo directly in your browser.

Open Playground

Frequently Asked Questions

GPT 3.5 Turbo costs $0.000500 per 1,000 input tokens and $0.001000 per 1,000 output tokens.
GPT 3.5 Turbo is available from 3 providers. Vercel offers the best price.
Vercel offers GPT 3.5 Turbo at $0.500 per million input tokens, the lowest of 3 providers (input prices range from $0.500 to $1.50 per million tokens).
GPT 3.5 Turbo scores Aider 57.9 (43rd percentile). Only benchmarks with published data for this model are shown.
We compare GPT 3.5 Turbo with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All OpenAI Models

See pricing for all OpenAI models.

View all OpenAI models →