Gpt Realtime
Provider: openai ·
gpt-realtime Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $4.00 |
| Output | $16.00 |
| Cached input (read) | $0.40 |
💡 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
$6.12
per month
Saves $1.08 via caching
Medium
10M in / 2000k out
$61.20
per month
Saves $10.80 via caching
Large
100M in / 20000k out
$612
per month
Saves $108 via caching
Context
- Input window
- 32,000 tokens
- Max output
- 4,096 tokens
Capabilities
- ⬜ Vision (image input)
- ✅ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Gpt Realtime with similar models
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.