Text Standard
Price-optimized, high-throughput text
$0.1271M Tokens1
Choose your Instrument
Pick the right intelligence tier for your task, or route across them for peak performance at lower costs.
From zero to first request
in < 5 minutes
in < 5 minutes
Every AI task. Covered.
Text Prime
Reliable models for everyday tasks
$0.6881M Tokens1
Text Max
Frontier models for complex reasoning
$5.5261M Tokens1
Code Standard
Price-optimized, high-throughput code
$0.1561M Tokens1
Code Prime
Reliable models for daily coding work
$0.7041M Tokens1
Code Max
Frontier models for complex coding tasks
$4.4211M Tokens1
Agent Standard
Price-optimized, high-throughput agents
$0.1561M Tokens1
Agent Prime
Reliable models for daily agent work
$0.6961M Tokens1
Agent Max
Frontier models for complex agent tasks
$5.5261M Tokens1
1Prices shown are based on a trailing 30-day blended average (input and output combined into a single per-1M-tokens rate) and may change as the market moves. Visit The Grid App to view real-time markets and pricing.
2The qualifying model list changes as new models meet the instrument spec and existing models are updated. Any model and supplier that qualifies the performance specification can serve requests on that instrument. The models listed here were recently active but are not guaranteed at any given time.
Route efficiently to get more out of every dollar.
Point each task to the right instrument to see improvements in performance and cost efficiency.
Triage on Standard,reason on Prime.
Classify requests on Standard first. Send onlythose that need reasoning to Prime.
Retrieve on Standard,synthesize on Prime.
Run retrieval and reranking on Standard. Generatethe final output on Prime.
Prime by default,Max by exception.
Keep your production workload on Prime. Use Maxonly for large inputs or where accuracy is critical.
Learn more on our blog
Read the Research
