Models

8 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
Qwen3.5 122B-A10B	neon	262,144	Input $0.22 per 1M tokens low Output $2.20 per 1M tokens low
Llama-3.3-70B-Instruct	neon	128,000	Input $0.50 per 1M tokens low Output $1.50 per 1M tokens low
GPT-5.2	neon	400,000	Input $1.75 per 1M tokens low Input (cached read) $0.175 per 1M tokens low Output $14.00 per 1M tokens low
Llama 3.1 8B Instruct	neon	131,072	Input $0.15 per 1M tokens low Output $0.45 per 1M tokens low
GPT-5.1	neon	400,000	Input $1.25 per 1M tokens low Input (cached read) $0.125 per 1M tokens low Output $10.00 per 1M tokens low
GPT-5.5 Pro	neon	1,050,000	Input $30.00 per 1M tokens low Input (>272k ctx) $60.00 per 1M tokens low Output $180.00 per 1M tokens low Output (>272k ctx) $270.00 per 1M tokens low
Gemma 3 12B	neon	131,072	Input $0.15 per 1M tokens low Output $0.50 per 1M tokens low
GPT-5.4	neon	1,050,000	Input $2.50 per 1M tokens low Input (>272k ctx) $5.00 per 1M tokens low Input (cached read, >272k ctx) $0.50 per 1M tokens low Input (cached read) $0.25 per 1M tokens low …2 more prices