695 listed

Models

Language models for agents: hosted models with input and output prices per million tokens from OpenRouter (read daily; prices change often), and open-weights models from Hugging Face with license and downloads. Filter by tool calling, context window and price, or switch to the table to compare.

Cards Table

Showing 121–144 of 500

Model	Provider	Input $/M	Output $/M	Context	Tools	Weights
Llama 4 Scout	Meta	$0.1	$0.3	1.3M	Yes	Open
Llama Guard 4 12B	Meta	$0.18	$0.18	164K	—	Open
MiniMax M3reasoning	MiniMax	$0.3	$1.2	1M	Yes	Open
MiniMax M3.1 Flashreasoning	MiniMax	$0.15	$0.6	1M	Yes	Open
MiniMax-01	MiniMax	$0.2	$1.1	1M	—	Open
Ministral 3 14B 2512	Mistral	$0.2	$0.2	262K	Yes	Open
Ministral 3 3B 2512	Mistral	$0.1	$0.1	131K	Yes	Open
Ministral 3 8B 2512	Mistral	$0.15	$0.15	262K	Yes	Open
Mistral Nemo	Mistral	$0.029	$0.03	131K	Yes	Open
Mistral Small 3	Mistral	$0.05	$0.08	33K	—	Open
Mistral Small 3.1 24B	Mistral	$0.351	$0.555	128K	Yes	Open
Mistral Small 3.2 24B	Mistral	$0.075	$0.2	256K	Yes	Open
Mistral Small 4reasoning	Mistral	$0.15	$0.6	262K	Yes	Open
Mixtral 8x22B Instruct	Mistral	$2	$6	66K	Yes	Open
Muse Glimmer 30Breasoning	Meta	$0.3	$1.2	131K	Yes	Open
Muse Spark Openreasoning	Meta	$1.25	$4.25	1M	Yes	Open
NVIDIA-Nemotron-3.5-Bolt-E4B-BF16	NVIDIA	Self-host	—	—	—	Open
NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16	NVIDIA	Self-host	—	—	—	Open
Qwen2.5 VL 72B Instruct	Qwen	$0.8	$1	128K	—	Open
Qwen3 VL 235B A22B Instruct	Qwen	$0.21	$1.9	262K	Yes	Open
Qwen3 VL 30B A3B Instruct	Qwen	$0.15	$0.6	262K	Yes	Open
Qwen3 VL 30B A3B Thinkingreasoning	Qwen	$0.29	$1	262K	Yes	Open
Qwen3 VL 8B Instruct	Qwen	$0.25	$0.75	262K	Yes	Open
Qwen3.5 397B A17Breasoning	Qwen	$0.5	$3.6	262K	Yes	Open

Prices are USD per million tokens from OpenRouter, read daily. Providers change prices often; check the model page before you rely on one.