OpenAI should put Mixtral 8x7b in their API just to flex their low prices
Now offering mixtral inference for $0.000000/1B tokens Burn all our VC money idgaf!
Mixtral > Gemini Pro on the Chatbot Arena Leaderboard And that's just `mistral-small` - Mistral also has a mystery `mistral-medium` available on their API https://t.co/hAvw62blhn
.@OctoML is now serving the lowest-cost Mixtral MoE inference I've seen. Input: $0.20/million tokens Output: $0.50/million tokens https://t.co/S5Rg5QoUdH
Last week @MistralAI launched pricing for the Mixtral MoE: $2.00~ / 1M tokens. Hours later @togethercompute took the weights and dropped pricing by 70% to $0.60 / 1M. Days later @abacusai cut 50% deeper to $0.30 / 1M. Yesterday @DeepInfra went to $0.27 / 1M. Who’s next ??? 📉
OctoAI has crazy fast #Mixtral 8x7B for $0.20 / 1M input tokens, and $0.50 / 1M output tokens 😎 You can try it out here (login first) https://t.co/7YYFCTsZT9
Several companies, including MistralAI, TogetherCompute, AbacusAI, DeepInfra, and OctoML, have been competing to offer the lowest pricing for Mixtral MoE inference tokens. OctoML is currently providing the lowest-cost Mixtral MoE inference at $0.20 per million input tokens and $0.50 per million output tokens. This pricing has been significantly reduced from the initial $2.00 per million tokens launched by MistralAI. Additionally, another user is offering Mixtral inference for $0.000000 per billion tokens. The competition for the lowest pricing continues, with speculation about which company will further reduce their pricing next.