Gpt 5.4
Provider: azure ai ·
azure_ai/gpt-5.4 Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $2.50 |
| Output | $15.00 |
| Cached input (read) | $0.25 |
💡 With prompt caching, you save up to 90% 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
$4.83
per month
Saves $0.68 via caching
Medium
10M in / 2000k out
$48.25
per month
Saves $6.75 via caching
Large
100M in / 20000k out
$483
per month
Saves $67.50 via caching
Context
- Input window
- 1,050,000 tokens
- Max output
- 128,000 tokens
Capabilities
- ✅ Vision (image input)
- ✅ Function / tool calling
- ✅ Prompt caching
- ✅ Web search
- ✅ JSON / response schema
Compare Gpt 5.4 with similar models
Claude Sonnet 4 6
azure ai
$3.00 in
/ $15.00 out
Gpt 5.4 2026 03 05
azure ai
$2.50 in
/ $15.00 out
Llama 4 Maverick 17B 128E Instruct FP8
azure ai
$1.41 in
/ $0.35 out
Claude Opus 4 5
azure ai
$5.00 in
/ $25.00 out
Claude Opus 4 6
azure ai
$5.00 in
/ $25.00 out
Claude Opus 4 7
azure ai
$5.00 in
/ $25.00 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.