A cost-efficient version of GPT Audio. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.
Specifications
Context
128K
Maximum Output
16.4K
Inputtext, audio
Outputtext, audio
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Pricing
Input$0.66/MTokens
Output$2.64/MTokens
Input Audio$11.00/MTokens
Output Audio$22.00/MTokens
Availability Trend (24h)
Performance Metrics (24h)
Similar Models
$1.21/$4.84/M
ctx200Kmax100Kavail—tps—
A cost-efficient reasoning model that excels at STEM tasks, particularly science, math, and coding.
$1.21/$4.84/M
ctx200Kmax100Kavail—tps—
A smaller model optimized for fast, cost-efficient reasoning. Achieves remarkable performance for its size, particularly in math, coding, and visual tasks.
$1.21/$4.84/M
ctx200Kmax100Kavail—tps—
InOutCap
Snapshot of o4-mini from April 16, 2025. Fast, cost-efficient reasoning model excelling at math, coding, and visual tasks.
$1.21/$4.84/M
ctx200Kmax100Kavail—tps—
InOutCap
Snapshot of o3-mini from January 31, 2025. Cost-efficient reasoning model for STEM tasks.