Compare OpenAI, Anthropic, Gemini model APIs
Easily compare the most popular LLM APIs across tokens limit, price, rate limits, latency, language and training data cutoff.
Provider
OpenAI
OpenAI
OpenAI
OpenAI
OpenAI
Anthropic
Anthropic
Google
Google
Mistral
Model
gpt-4o
gpt-4o-mini
gpt-4-turbo
gpt-4
gpt-3.5-turbo
claude-3.5-sonnet
claude-3-haiku
gemini-1.5-flash
gemini-1.5-pro
mistral-large
Max tokens
128,000
128,000
128,000
8,192
16,384
200,000
200,000
Max input tokens: 1048576.
Max output tokens: 8192.
Input price over 128K tokens: $0.15 / 1M tokens.
Output price over 128K tokens: $0.60 / 1M tokens.
Max input tokens: 1048576.
Max output tokens: 8192.
Input price over 128K tokens: $7 / 1M tokens.
Output price over 128K tokens: $21 / 1M tokens.
128,000
Input price per 1M tokens
$5.00
$0.15
$10.00
$30.00
$0.50
$3.00
$0.25
$0.07
$3.50
$3.00
Output price per 1M tokens
$15.00
$0.60
$30.00
$60.00
$1.50
$15.00
$1.25
$0.30
$10.50
$9.00
Default requests per minute
500
500
500
500
3,500
50
50
1,000
360
1,800
Default tokens per minute
30,000
200,000
30,000
10,000
200,000
40,000
50,000
4,000,000
4,000,000
50,000,000
Avg latency in the last 48h*
N/A
N/A
N/A
N/A
N/A
N/A
N/A
N/A
N/A
N/A
Training data cutoff
Oct 2023
Oct 2023
Dec 2023
Sep 2021
Sep 2021
Apr 2024
Aug 2023
Nov 2023
Nov 2023
Jan 2024
Languages available
All
All
All
All
All
All
All
All
All
All
*The average latency is calculated by generating a random 512 tokens every 10 minutes across 3 different locations. Check out our latency tracker.