📊 Live API Cost & Latency — May 2026
Price per 1M tokens. Click a column to sort.
ModelInput /1MOutput /1MLatency (TTFT)
GPT-4o mini$0.15$0.600.6s
Claude 3 Haiku$0.25$1.250.5s
Gemini 1.5 Flash$0.35$1.050.7s
Llama 3.1 70B$0.59$0.791.1s
Mistral Large$2.00$6.001.4s
Claude 3.5 Sonnet$3.00$15.001.8s
Gemini 1.5 Pro$3.50$10.501.2s
GPT-4o$5.00$15.000.9s
Updated May 2026. Run your own benchmark with your prompts →

Compare AI Models. Choose Smarter.

Run side-by-side comparisons with your actual prompts. See quality, cost, and speed — together.

🔍 Free
Try before you buy
$0
  • ✓5 comparisons/month
  • ✓Side-by-side output view
  • ✓GPT-4o + Claude 3.5 + Gemini
  • ✓Latency benchmarks
  • ✓Cost-per-token charts
  • ✓Community benchmark results
Most Popular
⚡ Pro
For individual AI builders
$29/mo
7-day free trial
  • ✓Unlimited comparisons
  • ✓All 20+ models
  • ✓Shareable comparison links
  • ✓Save & export results
  • ✓Custom system prompts
  • ✓Cost calculator (your usage)
  • ✓Prompt history (30 days)
  • ✓Priority support

14-day free trial. No credit card required.

🏢 Team
For teams evaluating LLMs
$99/mo
7-day free trial
  • ✓Everything in Pro
  • ✓Up to 5 team seats
  • ✓Shared prompt library
  • ✓Team comparison history (90 days)
  • ✓Bulk benchmark runner
  • ✓API access
  • ✓CSV/JSON export
  • ✓Custom model catalog
  • ✓Dedicated Slack support

14-day free trial. No credit card required.

7-day free trial on all paid plans. Cancel anytime. Payments secured by Stripe.

Powered by RITAC Solutions LLC