About
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
Related Models
Pricing
Input
$3.00
per 1M tokens
Output
$4.00
per 1M tokens
Blended
$3.25
per 1M tokens
Cheaper than 22% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.25
Monthly
$97.50
vs. Similar Models
GLM-5.2 (Non-reasoning)
$3.16-3%
Google: Gemini 3.5 Flash
$3.38+4%
Gemini 3.5 Flash (medium)
$3.38+4%
Gemini 3.5 Flash (minimal)
$3.38+4%
Performance
Context Window
16K
tokens
Larger than 6% of models
Max Output
4K
tokens
25% of context
Context Window Comparison
OpenAI: GPT-3.5 Turbo
16KSame
Microsoft: Phi 4
16K1.0x smaller
Llama 3.1 8B Instruct
16K1.0x smaller