Dolphin 2.9.2 Mixtral 8x22B 🐬

cognitivecomputations/dolphin-mixtral-8x22b

Created Jun 8, 202416,000 context
$0.90/M input tokens$0.90/M output tokens

Dolphin 2.9 is designed for instruction following, conversational, and coding. This model is a finetune of Mixtral 8x22B Instruct. It features a 64k context length and was fine-tuned with a 16k sequence length using ChatML templates.

This model is a successor to Dolphin Mixtral 8x7B.

The model is uncensored and is stripped of alignment and bias. It requires an external alignment layer for ethical use. Users are cautioned to use this highly compliant model responsibly, as detailed in a blog post about uncensored models at erichartford.com/uncensored-models.

#moe #uncensored

Providers for Dolphin 2.9.2 Mixtral 8x22B 🐬

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

NovitaAI
US
Context
16K
Max Output
16K
Input
$0.90
Output
$0.90

Apps using Dolphin 2.9.2 Mixtral 8x22B 🐬

Top public apps this week using this model

1.
Favicon for https://sillytavern.app/
SillyTavern
LLM frontend for power users
1.26Mtokens
2.
Favicon for https://openrouter.ai/chat
OpenRouter: Chatroom
Chat with multiple LLMs at once
826Ktokens
3.
Favicon for https://art-from-the-machine.github.io/
Mantella
Skyrim & Fallout 4 mod, naturally speak to NPCs
746Ktokens
4.
Favicon for https://openwebui.com/
Open WebUI
Extensible, self-hosted AI interface
628Ktokens
5.
Favicon for https://chub.ai/
Chub AI
GenAI for everyone
565Ktokens
6.
Favicon for https://litellm.ai/
liteLLM
Open-source library to simplify LLM calls
395Ktokens
7.
Favicon for https://modal-labs.github.io/website/
Modal Poe Bot
new
199Ktokens
8.
Favicon for https://apps.apple.com/
Pal Chat (iOS)
new
161Ktokens
9.
Favicon for https://opencharacter.org/
OpenCharacter
Open-source recreation of the old c.ai site
128Ktokens
10.
Favicon for https://roocode.com/
Roo Code
A whole dev team of AI agents in your editor
125Ktokens
11.
Favicon for https://librechat.ai/
LibreChat
Feature-rich, open-source ChatGPT clone
96Ktokens
12.
Favicon for https://radjourney.radbro.xyz/
radjourney
new
65Ktokens
13.
Favicon for https://boltai.com/
PDF Pals
new
39Ktokens
14.
Favicon for https://zapcalculator.com/
Generic smart calculators, fill in the values you have!
new
34Ktokens
15.
Favicon for https://www.typingmind.com/
TypingMind
A better UI for ChatGPT
32Ktokens
16.
Favicon for https://novelcrafter.com/
novelcrafter
Your personal novel writing toolbox. Plan, write and tinker with your story.
32Ktokens
17.
Favicon for https://anythingllm.com/
AnythingLLM
new
29Ktokens
18.
Favicon for https://labs.writingmate.ai/
ChatLabs.pro
new
27Ktokens
19.
Favicon for https://apipie.ai/
APIpie.ai
new
23Ktokens
20.
Favicon for https://github.com/zerebro-bot
Zerebro Bot
new
21Ktokens

Recent activity on Dolphin 2.9.2 Mixtral 8x22B 🐬

Tokens processed per day

Feb 7Feb 13Feb 23Mar 1Mar 7Mar 13Mar 19Mar 25Mar 31Apr 6Apr 12Apr 18Apr 24Apr 30May 608.5M17M25.5M34M

Uptime stats for Dolphin 2.9.2 Mixtral 8x22B 🐬

Uptime stats for Dolphin 2.9.2 Mixtral 8x22B 🐬 on the only provider

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it.

Learn more about our load balancing and customization options.

Sample code and API for Dolphin 2.9.2 Mixtral 8x22B 🐬

OpenRouter normalizes requests and responses across providers for you.

OpenRouter provides an OpenAI-compatible completion API to 300+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

from openai import OpenAI

client = OpenAI(
  base_url="https://openrouter.ai/api/v1",
  api_key="<OPENROUTER_API_KEY>",
)

completion = client.chat.completions.create(
  extra_headers={
    "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
    "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
  },
  extra_body={},
  model="cognitivecomputations/dolphin-mixtral-8x22b",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.

More models from Cognitive Computations

Dolphin3.0 R1 Mistral 24B

Dolphin 3.0 R1 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

The R1 version has been trained for 3 epochs to reason using 800k reasoning traces from the Dolphin-R1 dataset.

Dolphin aims to be a general purpose reasoning instruct model, similar to the models behind ChatGPT, Claude, Gemini.

Part of the Dolphin 3.0 Collection Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations

Dolphin3.0 Mistral 24B

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

Dolphin aims to be a general purpose instruct model, similar to the models behind ChatGPT, Claude, Gemini.

Part of the Dolphin 3.0 Collection Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations

Dolphin Llama 3 70B 🐬

Dolphin 2.9 is designed for instruction following, conversational, and coding. This model is a fine-tune of Llama 3 70B. It demonstrates improvements in instruction, conversation, coding, and function calling abilities, when compared to the original.

Uncensored and is stripped of alignment and bias, it requires an external alignment layer for ethical use. Users are cautioned to use this highly compliant model responsibly, as detailed in a blog post about uncensored models at erichartford.com/uncensored-models.

Usage of this model is subject to Meta's Acceptable Use Policy.

Dolphin 2.6 Mixtral 8x7B 🐬

This is a 16k context fine-tune of Mixtral-8x7b. It excels in coding tasks due to extensive training with coding data and is known for its obedience, although it lacks DPO tuning.

The model is uncensored and is stripped of alignment and bias. It requires an external alignment layer for ethical use. Users are cautioned to use this highly compliant model responsibly, as detailed in a blog post about uncensored models at erichartford.com/uncensored-models.

#moe #uncensored

    Dolphin 2.9.2 Mixtral 8x22B 🐬 - API, Providers, Stats | OpenRouter