Models

5,733 models shown. Amounts are per the unit stated in each row.
Model	Provider	Context	Prices
meta-llama/Meta-Llama-3-8B-Instruct-Turbo	meta	—	Input $0.18 per 1M tokens low Output $0.18 per 1M tokens low
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	meta	—	Input $0.88 per 1M tokens low Output $0.88 per 1M tokens low
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo	meta	—	Input $0.18 per 1M tokens low Output $0.18 per 1M tokens low
meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo	meta	—	Input $0.88 per 1M tokens low Output $0.88 per 1M tokens low
microsoft/phi-2	microsoft	—	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
mistralai/Mistral-7B-v0.1	mistral	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
mistralai/Mixtral-8x7B-Instruct-v0.1	mistral	—	Input $0.90 per 1M tokens low Output $0.90 per 1M tokens low
mistralai/Mixtral-8x7B-v0.1	mistral	—	Input $0.90 per 1M tokens low Output $0.90 per 1M tokens low
openchat/openchat-3.5-1210	openchat	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
snorkelai/Snorkel-Mistral-PairRM-DPO	snorkelai	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
teknium/OpenHermes-2-Mistral-7B	teknium	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
teknium/OpenHermes-2p5-Mistral-7B	teknium	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/GPT-JT-Moderation-6B	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/Llama-2-7B-32K-Instruct	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/RedPajama-INCITE-7B-Base	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/RedPajama-INCITE-7B-Chat	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/RedPajama-INCITE-7B-Instruct	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/RedPajama-INCITE-Base-3B-v1	togethercomputer	—	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
togethercomputer/RedPajama-INCITE-Chat-3B-v1	togethercomputer	—	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
togethercomputer/RedPajama-INCITE-Instruct-3B-v1	togethercomputer	—	Input $0.10 per 1M tokens low Output $0.10 per 1M tokens low
togethercomputer/StripedHyena-Hessian-7B	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/StripedHyena-Nous-7B	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
togethercomputer/alpaca-7b	togethercomputer	—	Input $0.20 per 1M tokens low Output $0.20 per 1M tokens low
upstage/SOLAR-10.7B-Instruct-v1.0	upstage	—	Input $0.30 per 1M tokens low Output $0.30 per 1M tokens low
zero-one-ai/Yi-34B	zero-one-ai	—	Input $0.80 per 1M tokens low Output $0.80 per 1M tokens low