Context
1.1M
Input
$0.10/M
Output
$0.50/M
Aliases:chatgpt-6-lunagpt6-lunaluna
OpenAI's most affordable and fastest GPT-6 model with a 1M+ context window, optimized for high-volume, latency-sensitive applications at minimal cost.
bedrock/gpt-6-lunaQuantUnspecified
- Input
- $0.10/M
- Output
- $0.50/M
- Context
- 1.1M
- Max out
- 128K
- Cache read
- $0.01/M
- Cache write cache_write_tokens
- $0.13/M
- Thinking out
- $0.50/M