WWhichAITry via Vercel AI Gateway
Models/OpenAI
OpenAI · released 2025-09

o4

Reasoning model. Thinks before it speaks.

context
200K
output max
100K
input /M
$15.00
output /M
$60.00
modalities
T·I
Verdict

What it's actually good at

Strengths

  • +State-of-the-art math & science
  • +Complex planning

Weaknesses

  • High latency
  • Expensive for chat

Our scores

reasoning
10.0
coding
9.0
writing
7.0
speed
3.0
value
5.0
Extended-thinking reasoning model for hard math, science, and planning. Slower and pricier per call, but far stronger on proofs and agents.
Pricing

Cost at common volumes

Monthly volumeInputOutputEst. monthly
Side project1M tok0.3M tok$33.00
Growing app50M tok15M tok$1650.00
Production500M tok150M tok$16500.00
Scale5000M tok1500M tok$165000.00

Estimates assume uncached input. Prompt caching and batch APIs can cut this by 50–90% for many workloads. Use the calculator →

Head-to-head

Compare o4