Models

7 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
Qwen3.8 Max	scx-ai	1,000,000	Input $1.82 per 1M tokens unverified · disputed Input (cache write) $2.50 per 1M tokens low Input (cached read) $0.17 per 1M tokens unverified · disputed Output $5.45 per 1M tokens unverified · disputed
GLM-5.2	scx-ai	1,048,576	Input $1.40 per 1M tokens unverified · disputed Input (cache write) $0.00 per 1M tokens low Input (cached read) $0.111 per 1M tokens unverified · disputed Output $4.40 per 1M tokens unverified · disputed
MiniMax-M2.7	scx-ai	204,800	Input $0.30 per 1M tokens low Input (cache write) $0.375 per 1M tokens low Input (cached read) $0.06 per 1M tokens low Output $1.20 per 1M tokens low
Qwen3 32B (SCX.ai (Turbo))	scx-ai	32,768	Input $0.36 per 1M tokens low Output $0.87 per 1M tokens low
Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))	scx-ai	131,072	Input $0.53 per 1M tokens low Output $1.62 per 1M tokens low
Gemma 4 31B IT (SCX.ai (Turbo))	scx-ai	131,072	Input $0.30 per 1M tokens low Output $0.91 per 1M tokens low
GPT OSS 120B (SCX.ai (Turbo))	scx-ai	131,072	Input $0.17 per 1M tokens low Output $0.55 per 1M tokens low