OpenAI tier routing

GPT-4o vs GPT-4o mini Cost

See how much you save by routing traffic from GPT-4o to GPT-4o mini on the same token volume.

See sample costs Custom calculator

OpenAI

GPT-4o

Provider: OpenAI
Modality: text
Context: 128,000
Input / 1M: $2.50
Output / 1M: $10.00
Cached / 1M: $1.25
Batch discount: 50%

View model page →

OpenAI

GPT-4o mini

Provider: OpenAI
Modality: text
Context: 128,000
Input / 1M: $0.15
Output / 1M: $0.60
Cached / 1M: $0.075
Batch discount: 50%
Training / 1M: $3.00

View model page →

Sample workload

Estimated spend on a shared scenario

Catalog rates updated 2026-07-31. Same inputs on both models for an apples-to-apples read.

GPT-4o

10k × 2k/500 tokens

$100.00

GPT-4o mini

10k × 2k/500 tokens

$6.00

Lower cost

GPT-4o mini is lower by $94.00 on this sample workload.

Open cost calculator Batch vs realtime All comparisons

Keep comparing

More matchups

General chat and coding assistantsClaude Sonnet 4 vs GPT-4o Cost High-volume product featuresGemini 2.5 Flash vs GPT-4o mini Cost Long-context reasoningClaude Opus 4 vs o3 Cost Flagship assistant routingGemini 2.5 Pro vs Claude Sonnet 4 Cost

Approximate static list prices for planning only. Always verify against each provider’s official pricing page before production budgeting.