OpenAI: GPT-3.5 Turbo (older v0613)

deprecatedproprietary

GPT-3.5 Turbo is OpenAI's fastest model.

Intelligence
Speed
Context
4K
Max output
4K
Input price
$1/1M tokens
Output price
$2/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Batch Processing
Fine-tuning

Details

Model IDopenai/gpt-3.5-turbo-0613
Provider OpenRouter
Creator OpenAI
Familygpt-3.5
Licenseproprietary
Statusdeprecated
Typechat
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window4K tokens
Max input—
Max output4K tokens
Reasoning tokens—
Knowledge cutoff
Release date
Deprecation date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$1
Output
$2
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: gpt-3.5

ModelContextMax outPricing
OpenAI: GPT-3.5 Turbo (batch)16K4K$0.25$0.75
OpenAI: GPT-3.5 Turbo16K4K$0.5$1.5
OpenAI: GPT-3.5 Turbo (older v0613)4K4K$1$2
OpenAI: GPT-3.5 Turbo Instruct4K4K$1.5$2
OpenAI: GPT-3.5 Turbo 16k16K4K$3$4

API

GET/v1/models/openrouter/openai/gpt-3.5-turbo-0613

OpenAI: GPT-3.5 Turbo (older v0613)

deprecated
openai/gpt-3.5-turbo-0613

GPT-3.5 Turbo is OpenAI's fastest model.

Changes · 5 entries
openai/gpt-3.5-turbo-0613updateca7a400Nov 2, 2026, 03:02 AM
max_output_tokens4096→3685
openai/gpt-3.5-turbo-0613updatee3d7dedAug 31, 2026, 04:13 AM
max_output_tokens4096→3685
openai/gpt-3.5-turbo-0613update1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
openai/gpt-3.5-turbo-0613update2b100acMar 23, 2026, 05:30 AM
model_typechat
release_date2024-01-25
taglineGPT-3.5 Turbo is OpenAI's fastest model.
tools["function_calling"]
openai/gpt-3.5-turbo-0613create7f5c66fMar 21, 2026, 05:16 AM