Find the Best Deals on Cutting-Edge Language Model Endpoints
Explore and compare prices of state-of-the-art Large Language Models (LLMs) from different providers. Find cost-effective and advanced models for your needs. Make an informed decision with our user-friendly interface.
Enter your email address in this form to receive notifications about significant price changes and the addition of new models!
Provider | Model | Type | Input Price($)/1M Tokens | Output Price($)/1M Tokens |
---|---|---|---|---|
OpenAI | gpt-4-1106-preview | chat | 10 | 30 |
OpenAI | gpt-4-1106-vision-preview | chat | 10 | 30 |
OpenAI | gpt-4 | chat | 30 | 60 |
OpenAI | gpt-4-32k | chat | 60 | 120 |
OpenAI | gpt-3.5-turbo-1106 | chat | 1 | 2 |
OpenAI | gpt-3.5-turbo-instruct | chat | 1.5 | 2 |
OpenAI | ada v2 | embeddings | 0.1 | |
OpenAI | davinci-002 | base | 2 | |
OpenAI | babbage-002 | base | 0.4 | |
Mistral | mistral-tiny | chat | 0.1526 | 0.42 |
Mistral | mistral-small | chat | 0.654 | 1.8 |
Mistral | mistral-medium | chat | 2.725 | 7.5 |
Mistral | mistral-medium | embeddings | 0.10900000000000001 | |
Anyscale | Mistral-7B-OpenOrca | chat | 0.15 | 0.15 |
Anyscale | Mistral-7B-Instruct-v0.1 | chat | 0.15 | 0.15 |
Anyscale | Zephyr-7b-beta | chat | 0.15 | 0.15 |
Anyscale | Llama-Guard-7b | chat | 0.15 | 0.15 |
Anyscale | Llama-2-7b-chat-hf | chat | 0.15 | 0.15 |
Anyscale | Llama-2-13b-chat-hf | chat | 0.25 | 0.25 |
Anyscale | Mixtral-8x7B-Instruct-v0.1 | chat | 0.5 | 0.5 |
Anyscale | Llama-2-70b-chat-hf | chat | 1.0 | 1.0 |
Anyscale | CodeLlama-34b-Instruct-hf | chat | 1.0 | 1.0 |
Anyscale | thenlper-gte-large | chat | 0.05 | 0.05 |
Together | up to 4B | chat | 0.1 | 0.1 |
Together | 4.1B to 8B | chat | 0.2 | 0.2 |
Together | 8B to 21B | chat | 0.3 | 0.3 |
Together | 21B to 41B | chat | 0.8 | 0.8 |
Together | 41B to 70B | chat | 0.9 | 0.9 |
Together | llama-7b | chat | 0.2 | 0.2 |
Together | llama-13b | chat | 0.225 | 0.225 |
Together | llama-13b | chat | 0.9 | 0.9 |
Together | mixture of experts 8X7B | chat | 0.6 | 0.6 |
DeepInfra | Llama-2-7b-chat | chat | 0.13 | 0.13 |
DeepInfra | Mistral-7B | chat | 0.13 | 0.13 |
DeepInfra | OpenChat-3.5 | chat | 0.13 | 0.13 |
DeepInfra | MistralLite | chat | 0.13 | 0.13 |
DeepInfra | Yi-6B-200K | chat | 0.13 | 0.13 |
DeepInfra | Llama-2-13b-chat | chat | 0.22 | 0.22 |
DeepInfra | MythoMax-L2-13b | chat | 0.22 | 0.22 |
DeepInfra | mixtral-8x7B-chat | chat | 0.27 | 0.27 |
DeepInfra | Yi-34B-Chat | chat | 0.6 | 0.6 |
DeepInfra | CodeLlama-34b-Instruct | chat | 0.6 | 0.6 |
DeepInfra | Phind-CodeLlama-34B-v2 | chat | 0.6 | 0.6 |
DeepInfra | Llama-2-70b-chat | chat | 0.7 | 0.9 |
DeepInfra | Airoboros-70b | chat | 0.7 | 0.9 |
DeepInfra | Lzlv-70b | chat | 0.7 | 0.9 |
MosaicML | Instructor-Large | chat | 0.1 | 0.1 |
MosaicML | Instructor-XL | chat | 0.2 | 0.2 |
MosaicML | Llama-2-70b-Chat | chat | 2 | 2 |
MosaicML | MPT-30B Instruct | chat | 1 | 1 |
MosaicML | MPT-7B Instruct(fastest) | chat | 0.5 | 0.5 |