Gpt 4.5 Preview

Provider: azure · azure/gpt-4.5-preview

Pricing per million tokens

Component USD per 1M tokens
Input $75.00
Output $150
Cached input (read) $37.50

💡 With prompt caching, you save up to 50% on cached input tokens — massive for repeated context like system prompts, RAG retrieval, or long conversations.

Monthly cost estimates

Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.

Small
1M in / 200k out
$93.75
per month
Saves $11.25 via caching
Medium
10M in / 2000k out
$938
per month
Saves $113 via caching
Large
100M in / 20000k out
$9375
per month
Saves $1125 via caching

Context

Input window
128,000 tokens
Max output
16,384 tokens

Capabilities

  • ✅ Vision (image input)
  • ✅ Function / tool calling
  • ✅ Prompt caching
  • ⬜ Web search
  • ✅ JSON / response schema

Compare Gpt 4.5 Preview with similar models

Gpt 4 32k
azure
$60.00 in / $120 out
Gpt 4 32k 0613
azure
$60.00 in / $120 out
Command R Plus
azure
$3.00 in / $15.00 out
Gpt 4o 2024 08 06
azure
$2.75 in / $11.00 out
Gpt 4o 2024 11 20
azure
$2.75 in / $11.00 out
Gpt 4o Mini 2024 07 18
azure
$0.17 in / $0.66 out

Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.