gpt-3.5-turbo-1106 with 16k input context length at no greater cost.
Specifications
Context16,385
Max Output4,096
Inputtext
Outputtext, json
Performance (7-day Average)
Uptime
TPS
RURT
API Paths
/v1/chat/completions
Pricing
Input$3.00× 1.1/ MTokens
Output$4.00× 1.1/ MTokens
Batch Input$1.50× 1.1/ MTokens
Batch Output$2.00× 1.1/ MTokens