Back to models
retired

OpenAI: GPT-3.5 Turbo (older v0613)

openai/gpt-3-5-turbo

Prices

Input

$0.50 per 1M tokens

high
Input (batch)

$1.00 per 1M tokens

low
Input (cached read)

$0.00 per 1M tokens

low
Output

$1.50 per 1M tokens

high
Output (batch)

$2.00 per 1M tokens

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

17 sales channels for this model.
ChannelWhatPrice
Microsoft AzureInput$1.00 per 1M tokens
Output$2.00 per 1M tokens
Microsoft Azure · azure-aiInput$1.00 per 1M tokens
Output$2.00 per 1M tokens
OpenRouter · openaiInput$1.00 per 1M tokens
Output$2.00 per 1M tokens
OpenRouterInput$1.00 per 1M tokens
Output$2.00 per 1M tokens
Other · aimlapiInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · edenaiInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · impossiblInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · kiloInput$1.00 per 1M tokens
Output$2.00 per 1M tokens
Other · llmgatewayInput$0.50 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$1.50 per 1M tokens
Other · llmgateway-providersInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · merge-gatewayInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · nano-gptInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · openrouterInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · orcarouterInput$0.50 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$1.50 per 1M tokens
Other · poeInput$0.45 per 1M tokens
Output$1.40 per 1M tokens
Other · vercelInput$0.50 per 1M tokens
Output$1.50 per 1M tokens
Other · vercel-ai-gatewayInput$0.50 per 1M tokens
Output$1.50 per 1M tokens

Specifications

Provider
openai
Context window
4,095
Max output tokens
4,096
Open weights
no
Released
03/01/2023
Retires
10/23/2026
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
0.5 per 1M tokens, unchanged since 09/14/2026
Output
1.5 per 1M tokens, unchanged since 09/14/2026
Input (batch)
1 per 1M tokens, unchanged since 09/15/2026
Output (batch)
2 per 1M tokens, unchanged since 09/15/2026
Input (cached read)
0 per 1M tokens, unchanged since 10/20/2026

Last updated 11/19/2026, 01:12