LLM Index

Overview and comparison of available providers and models

Provider
Model
Mode
Status
Release date
Deprecation date
Max. tokens
Token price in / out (1k)
Links
AI21Jurassic 2 Light
completion
available
Mar 9, 20238,1920.003
Jurassic 2 Mid
completion
available
Mar 9, 20238,1920.01
Jurassic 2 Ultra
completion
available
Mar 9, 20238,1920.015
Aleph AlphaLuminous Base
completion
available
Apr 14, 20232,0480.03
Luminous Base Control
chat
available
Apr 14, 20232,0480.0375
Luminous Extended
completion
available
Apr 14, 20232,0480.045
Luminous Extended Control
chat
available
Apr 14, 20232,0480.05625
Luminous Supreme
completion
available
Apr 14, 20232,0480.175
Luminous Supreme Control
chat
available
Apr 14, 20232,0480.21875
AnthropicClaude 2
chat
available
Jul 11, 2023100,0000.008 / 0.024
Claude 2.1
chat
available
Nov 21, 2023200,0000.008 / 0.024
Claude Instant 1
chat
available
Mar 14, 2023100,0000.00163 / 0.00551
Claude Instant 1.2
chat
available
Sep 21, 2023100,0000.00163 / 0.00551
CohereCommand
completion
available
4,0960.015
Command Light
completion
available
4,0960.015
Command Nightly
completion
available
4,0960.015
Deep InfraCode Llama 34B Instruct HF
chat
Aug 24, 20234,0960.0006
Llama 2 13B Chat HF
chat
available
Jul 18, 20234,0960.00035
Llama 2 70B Chat HF
chat
available
Jul 18, 20236,1440.001875
Llama 2 7B Chat HF
chat
available
Jul 18, 20234,0960.0002
Mistral 7B Instruct v0.1
chat
available
Sep 27, 20234,0960.0002
NLP CloudChat Dolphin
chat
available
2,0480.02
Dolphin
completion
available
2,0480.02
OpenAIAda 001
completion
available
Jun 11, 2020Jan 4, 20242,0490.0004
Babbage 001
completion
available
Jun 11, 2020Jan 4, 20242,0490.0005
Curie 001
completion
available
Jun 11, 2020Jan 4, 20242,0490.002
DaVinci 003
completion
available
Nov 28, 2022Jan 4, 20244,0970.02
GPT-3.5 Turbo
chat
available
Nov 30, 20224,0960.0015 / 0.002
GPT-3.5 Turbo 0301
chat
available
4,0960.0015 / 0.002
GPT-3.5 Turbo 0613
chat
available
4,0960.0015 / 0.002
GPT-3.5 Turbo 1106
chat
available
Nov 6, 202316,3850.001 / 0.002
GPT-3.5 Turbo 16k
chat
available
Nov 30, 202216,3840.003 / 0.004
GPT-3.5 Turbo 16k 0301
chat
available
16,3840.003 / 0.004
GPT-3.5 Turbo 16k 0613
chat
available
16,3840.003 / 0.004
GPT-3.5 Turbo Instruct
completion
available
4,0960.0015 / 0.002
GPT-4
chat
available
Mar 14, 20238,1920.03 / 0.06
GPT-4 0301
chat
available
8,1920.03 / 0.06
GPT-4 0613
chat
available
8,1920.03 / 0.06
GPT-4 32k
chat
available
Mar 14, 202332,7680.06 / 0.12
GPT-4 32k 0301
chat
available
32,7680.06 / 0.12
GPT-4 32k 0613
chat
available
32,7680.06 / 0.12
GPT-4 Turbo
chat
available
Nov 6, 2023128,0000.01 / 0.03
PaLM 2Chat Bison
chat
available
May 10, 20234,0960.0005
Code Bison
completion
available
May 10, 20236,1440.0005
Text Bison
completion
available
May 10, 20238,1920.0005
PerplexityCode Llama 34B
chat
available
Oct 4, 20234,0960
Llama 2 70B
chat
available
Oct 4, 20234,0960
Mistral 7B
chat
available
Oct 4, 20234,0960
OpenHermes 2 Mistral 7B
chat
available
Oct 16, 20234,0960
OpenHermes 2.5 Mistral 7B
chat
available
Oct 16, 20234,0960
pplx 70B chat alpha
chat
available
Oct 27, 20234,0960
pplx 7B chat alpha
chat
available
Oct 27, 20234,0960
xAIGrok 1
chat
Nov 6, 202025,000

You can find an overview of model parameter support for each available model in the LiteLLM docs.

If you are missing a provider or model that you would like to use inside PROMPTMETHEUS, please don't hesitate to request it. The goal is to support all relevant foundation models and eventually even custom models. Shoutout to Krrish and Ishaan from LiteLLM who make this possible.

Disclaimer: Even though we try to keep this list accurate and up-to-date, please do not rely on the presented information for critical use cases and always double check official sources.


How to choose the right LLM for my use case?

Unfortunately, there is no universal answer to this question. It depends on your use case, your budget, and your personal preferences. A good strategy to go about it is to do the following:

If you are new to the game, start with the industry standard, GPT-3.5 for simple tasks and GPT-4 for more complex ones. Use PROMPTMETHEUS to experiment until you get satisfying and reproducable results. If you do not get anywhere with OpenAI, try different providers. Once you have a working prompt, try to optimize it for performance, speed, reliability, and cost by comparing different LLMs and model parameters. As a rule of thumb, the cheapest model which is fast enough and does the job is the best one.

If you are more experienced with Prompt Engineering and AI Development, start with the model that historically worked best for use cases similar to the one you have at hand. But before you go into fine-tuning of your prompt, take an early version and execute it with a few different LLMs to see which one is most promising. Use that one to fine-tune your prompt. Once you achieve great results, revisit your model choice and optimize for performance, speed, and reliability.

Please also check the "Building a Prompt Engineering IDE" and "Prompt Engineering Tips & Tricks" posts for more information.

Supported LLMs

Anthropic

Claude 2.1

Claude 2

Claude Instant 1.2

Claude Instant 1

Cohere

Command / Nightly

Command Light

OpenAI

GPT-4 Turbo

GPT-4 / 32k

GPT-3.5 Turbo / 16k

GPT-3.5 Turbo Instruct

DaVinci 003

Curie 001

Babbage 001

Ada 001

Perplexity

Llama 2 70B

Code Llama 34B

Mistral 7B Instruct

OpenHermes 2.5 Mistral 7B

OpenHermes 2 Mistral 7B

pplx 70B chat alpha

pplx 7B chat alpha

PaLM 2

Text Bison

Chat Bison

Code Bison

NLP Cloud

Chat Dolphin

Dolphin

Aleph Alpha

Luminous Supreme

Luminous Extended

Luminous Base

AI21 Labs

Jurassic 2 Ultra

Jurassic 2 Mid

Jurassic 2 Light

Deep Infra

Llama 2 70B Chat HF

Llama 2 13B Chat HF

Llama 2 7B Chat HF

Mistral 7B Instruct v0.1

xAI

coming soon...

Hugging Face

coming soon...

Replicate

coming soon...

Azure

coming soon...

Bedrock

coming soon...

Custom

coming soon...

Local

coming soon...