Models

5,705 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
meta-llama/llama-2-70b-chat	meta	4,096	Input $0.50 per 1M tokens low Input (cache write) $0.50 per 1M tokens low Input (cached read) $0.50 per 1M tokens low Output $1.50 per 1M tokens low
meta-llama/llama-3.1-405b	meta	8,000	Input $2.00 per 1M tokens low Output $2.00 per 1M tokens low
meta-llama/llama-guard-2-8b	meta	8,192	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
Llama Guard 3 8B	meta	131,072	Input $0.484 per 1M tokens low Output $0.03 per 1M tokens low
microsoft/phi-3-medium-128k-instruct	microsoft	128,000	Input $1.00 per 1M tokens low Output $1.00 per 1M tokens low
microsoft/phi-3-mini-128k-instruct	microsoft	131,072	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
microsoft/phi-3.5-mini-128k-instruct	microsoft	—	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
microsoft/wizardlm-2-7b	microsoft	—	Input $0.07 per 1M tokens low Output $0.07 per 1M tokens low
Midnight Rose 70B	openrouter	—	Input $0.80 per 1M tokens low Output $0.80 per 1M tokens low
MiniMax M1 (extended)	minimax	—	Input $0.55 per 1M tokens low Output $2.20 per 1M tokens low
mistralai/mistral-7b-instruct-v0.1	mistral	8,192	Input $1.92 per 1M tokens low Output $1.92 per 1M tokens low
mistralai/mistral-7b-instruct-v0.2	mistral	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
Mistral Nemo 12B Celeste	openrouter	—	Input $0.80 per 1M tokens low Output $1.20 per 1M tokens low
Mistral Nemo Inferor 12B	openrouter	—	Input $0.80 per 1M tokens low Output $1.20 per 1M tokens low
Starcannon 12B	openrouter	—	Input $0.80 per 1M tokens low Output $1.20 per 1M tokens low
Mythalion 13B	openrouter	—	Input $0.80 per 1M tokens low Output $1.20 per 1M tokens low
neversleep/llama-3-lumimaid-70b	neversleep	—	Input $3.38 per 1M tokens low Output $4.50 per 1M tokens low
neversleep/llama-3-lumimaid-8b	neversleep	—	Input $0.0938 per 1M tokens low Output $0.75 per 1M tokens low
neversleep/llama-3.1-lumimaid-70b	neversleep	—	Input $1.50 per 1M tokens low Output $2.25 per 1M tokens low
neversleep/llama-3.1-lumimaid-8b	neversleep	—	Input $0.0938 per 1M tokens low Output $0.75 per 1M tokens low
neversleep/noromaid-20b	neversleep	—	Input $0.75 per 1M tokens low Output $1.50 per 1M tokens low
Noromaid 20B	openrouter	—	Input $1.25 per 1M tokens low Output $2.00 per 1M tokens low
nothingiisreal/mn-celeste-12b	nothingiisreal	—	Input $0.80 per 1M tokens low Output $1.20 per 1M tokens low
nousresearch/nous-hermes-2-mixtral-8x7b-dpo	nousresearch	32,768	Input $0.50 per 1M tokens low Output $0.50 per 1M tokens low
OpenHands LM 32B V0.1	openrouter	—	Input $2.60 per 1M tokens low Output $3.40 per 1M tokens low