modelgrep
O

OpenAI: GPT-3.5 Turbo

openai/gpt-3.5-turbo

ToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
50
166th fastest
Latency
413ms
first token
Input price
$0.500
166th cheapest
Context
16K
4K max out

How it compares

Faster than44%
of all ranked models
Cheaper than44%
of all ranked models

Overview

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

Benchmarks

independent · via OpenRouter
Artificial Analysis
Coding Index
10.7
GPQA Diamond
30%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
OpenAI$0.500$1.50100%

Specifications

Context window16K
Max output4K
Knowledge cutoffSep 2021
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedYes

GPT-3.5 Turbo FAQ

How much does GPT-3.5 Turbo cost?

GPT-3.5 Turbo costs $0.500 per million input tokens and $1.50 per million output tokens via OpenRouter, making it 166th cheapest of 298 paid models.

How fast is GPT-3.5 Turbo?

GPT-3.5 Turbo generates around 50 tokens per second with 413ms time-to-first-token (p50), the 166th fastest tracked model.

What is GPT-3.5 Turbo's context window?

GPT-3.5 Turbo supports a 16K-token context window and can output up to 4K tokens. It accepts text input.

Compare head-to-head