Fireworks AI serverless pricing doc, re-read 2026-10-17

Fetched 2026-10-17. Standard cells are input / cached input / output USD per 1M. Named rows: OpenAI GPT OSS 120B $0.15 / $0.015 / $0.60 (Priority $0.18 / $0.018 / $0.72); DeepSeek V4.1 Flash $0.30 / $0.006 / $1.20; GLM 5.3 Flash $0.15 / $0.03 / $0.50; GLM 5.3 $1.40 / $0.26 / $4.40; MiniMax M3 $0.30 / $0.06 / $1.20; Kimi K3 $3.00 / $0.30 / $15.00; Qwen 3.8 Max $2.00 / $0.25 / $6.00. No Llama 3.3 row on the named table. Size-band fallback for unlisted text models is unchanged from 2026-10-14: under 4B $0.10, 4B-16B $0.20, over 16B $0.90, MoE up to 56B $0.50, MoE 56.1-176B $1.20, uniform on input and output. The gpt-oss-120b Standard price the service record uses did not move.