Standard · us-east-1 · StandardInputUS$0.9OutputUS$0.9Cache—USD / million tokensOfficial regional rate
Updated: AILYRE · MODEL PRICES
Llama 3.1 Instruct (70B) (w/ latency optimized inference) pricing
Compare Llama 3.1 Instruct (70B) (w/ latency optimized inference) API input, output and cache prices, original USD/CNY rates, free-access conditions and subscription allowances.
Choose currency and filter platforms ↗1 providersUpdated every 6 hours
LOWEST STANDARD ESTIMATE
AWS Bedrock US$1.125
For 1M input + 0.25M output tokens. CNY prices use the snapshot FX rate; eligibility and usage conditions appear below.
Standard · us-east-1 · StandardInputUS$0.9OutputUS$0.9Cache—USD / million tokensOfficial regional rate
Original APIs and platform prices
Snapshot updated: