Models

5,705 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
GLM 4.5 FP8	z-ai	131,072	Input $0.20 per 1M tokens low Output $0.80 per 1M tokens low
Qwen3 Coder 480B A35B Instruct	qwen	262,144	Input $0.20 per 1M tokens low Output $0.80 per 1M tokens low
Palmyra X4	writer	128,000	Input $2.50 per 1M tokens low Output $10.00 per 1M tokens low
Pixtral Large (25.02) (US)	mistral	128,000	Input $2.00 per 1M tokens low Output $6.00 per 1M tokens low
Qwen3 235B-A22B Instruct 2507	qwen	262,144	Input $0.22 per 1M tokens medium Input (batch) $0.11 per 1M tokens low Input (flex) $0.11 per 1M tokens low Output $0.88 per 1M tokens medium …2 more prices
Voxtral Mini 3B 2507	mistral	32,768	Input $0.04 per 1M tokens medium Input (flex) $0.02 per 1M tokens low Output $0.04 per 1M tokens medium Output (flex) $0.02 per 1M tokens low
NVIDIA Nemotron Nano 12B v2 VL BF16	nvidia	128,000	Input $0.20 per 1M tokens medium Input (flex) $0.10 per 1M tokens low Input (region: us-gov-east-1) $0.24 per 1M tokens low Input (region: us-gov-west-1) $0.24 per 1M tokens low …6 more prices
NVIDIA Nemotron Nano 3 30B	nvidia	262,144	Input $0.06 per 1M tokens medium Input (flex) $0.03 per 1M tokens low Input (region: us-gov-east-1) $0.072 per 1M tokens low Input (region: us-gov-west-1) $0.072 per 1M tokens low …6 more prices
DeepSeek-V3.1	deepseek	128,000	Input $0.58 per 1M tokens medium Output $1.68 per 1M tokens medium
Llama 4 Maverick 17B Instruct	meta	128,000	Input $0.24 per 1M tokens low Output $0.97 per 1M tokens low
Llama 3.3 70B Instruct (US)	meta	128,000	Input $0.72 per 1M tokens medium Input (region: us) $0.72 per 1M tokens medium Output $0.72 per 1M tokens medium Output (region: us) $0.72 per 1M tokens medium
Llama 3.1 70B Instruct (US)	meta	128,000	Input $0.72 per 1M tokens low Output $0.72 per 1M tokens low
Llama 4 Scout 17B Instruct (US)	meta	128,000	Input $0.17 per 1M tokens low Output $0.66 per 1M tokens low
Qwen3-Next 80B-A3B Instruct	qwen	262,144	Input $0.15 per 1M tokens medium Input (region: ap-northeast-1) $0.18 per 1M tokens low Input (region: ap-south-1) $0.18 per 1M tokens low Input (region: ap-southeast-2) $0.1545 per 1M tokens low …10 more prices
Qwen3-Coder 480B-A35B Instruct	qwen	131,072	Input $0.45 per 1M tokens medium Output $1.80 per 1M tokens medium
NVIDIA Nemotron 3 Super 120B A12B	nvidia	256,000	Input $0.15 per 1M tokens medium Input (flex) $0.075 per 1M tokens low Input (flex) (region: eu-west-2) $0.115 per 1M tokens low Input (region: eu-west-2) $0.23 per 1M tokens low …10 more prices
Devstral 2 123B	mistral	256,000	Input $0.40 per 1M tokens medium Input (flex) $0.20 per 1M tokens low Output $2.00 per 1M tokens medium Output (flex) $1.00 per 1M tokens low
DeepSeek-R1 (US)	deepseek	128,000	Input $1.35 per 1M tokens medium Input (region: us) $1.35 per 1M tokens medium Output $5.40 per 1M tokens medium Output (region: us) $5.40 per 1M tokens medium
Llama 3.1 8B Instruct	meta	128,000	Input $0.22 per 1M tokens low Output $0.22 per 1M tokens low
Dola Seed 2.0 Code (preview)	bytedance	131,072	Input $0.50 per 1M tokens low Output $3.00 per 1M tokens low
Seed 2.0 Code	bytedance	256,000	Input $0.40 per 1M tokens low Output $2.40 per 1M tokens low
Seed 2.0 Lite	bytedance	131,072	Input $0.25 per 1M tokens low Output $2.00 per 1M tokens low
Seed 2.0 Pro	bytedance	131,072	Input $0.50 per 1M tokens low Output $3.00 per 1M tokens low
Seed 2.0 Mini	bytedance	131,072	Input $0.10 per 1M tokens low Output $0.40 per 1M tokens low
DeepSeek V4 Flash 0731	deepseek	1,000,000	Input $0.28 per 1M tokens low Input (cached read) $0.07 per 1M tokens low Output $0.56 per 1M tokens low