Explore Mixes

Crosshatch Mixes combine the strengths of multiple AI models to deliver optimal performance for specific tasks. Each mix is carefully curated and automatically updated to ensure you always have access to the best AI capabilities without manual selection.

A specialized open-source mix optimized for engaging, multi-turn conversations and roleplay. Primarily powered by Hermes 3, a fine-tuned Llama 3.1 405B model, it excels in long-term context retention and adaptive responses.

Sep 9
$3.95/M input tokens$5.35/M output tokens

A mix that picks the highest-ranked model for Chinese prompts, based on LMSYS Chinese Leaderboard.

Oct 10
$4.22/M input tokens$12.65/M output tokens

A mix that picks the highest-ranked open-source model for Chinese prompts, based on LMSYS Chinese Leaderboard.

Oct 10
$1.19/M input tokens$2.60/M output tokens

Don't worry about staying up-to-date with the latest coding model to use in your favorite IDE. This mix will use the top coding models ranked in the LMSys Chatbot Arena for the Coding category

Aug 13
$4.56/M input tokens$14.19/M output tokens

The best non-commercial coding models according to the LMSys leaderboard. This mix will use the top coding models ranked in the LMSys Chatbot Arena for the Coding category without any proprietary models.

Aug 13
$2.44/M input tokens$2.67/M output tokens

A mix that picks the highest-ranked model for French prompts, based on LMSYS French Leaderboard.

Oct 10
$4.34/M input tokens$13.01/M output tokens

A mix that picks the highest-ranked model for French prompts, based on LMSYS French Leaderboard.

Oct 10
$2.87/M input tokens$4.46/M output tokens

A mix that picks the highest-ranked model for German prompts, based on LMSYS German Leaderboard.

Oct 10
$4.46/M input tokens$13.39/M output tokens

A mix that picks the highest-ranked model for German prompts, based on LMSYS German Leaderboard.

Oct 10
$3.26/M input tokens$5.79/M output tokens

A mix that picks the highest-ranked model for Japanese prompts, based on LMSYS Japanese Leaderboard.

Oct 10
$4.39/M input tokens$13.17/M output tokens

A mix that picks the highest-ranked model for Japanese prompts, based on LMSYS Japanese Leaderboard.

Oct 10
$2.52/M input tokens$4.94/M output tokens

A mix that picks the highest-ranked model for Korean prompts, based on LMSYS Korean Leaderboard.

Oct 10
$3.83/M input tokens$11.49/M output tokens

A mix that picks the highest-ranked model for Korean prompts, based on LMSYS Korean Leaderboard.

Oct 10
$1.76/M input tokens$1.76/M output tokens

Optimized for extended conversations, this mix utilizes top-performing models in multi-turn interactions. It leverages the LMSys Chatbot Arena rankings for conversations with two or more turns, ensuring high-quality responses in longer dialogues.

Sep 9
$4.54/M input tokens$14.38/M output tokens

Optimized for extended conversations, this mix utilizes top-performing models in multi-turn interactions. It leverages the LMSys Chatbot Arena rankings for conversations with two or more turns, ensuring high-quality responses in longer dialogues.

Sep 9
$8.27/M input tokens$30.51/M output tokens

Stay effortlessly current with the best general-purpose AI models. This mix automatically utilizes the top-ranked models from the LMSys Chatbot Arena's overall leaderboard, ensuring you always have access to the most capable AI for a wide range of tasks.

Sep 9
$4.45/M input tokens$13.34/M output tokens

Stay effortlessly current with the best general-purpose open-source AI models. This mix automatically utilizes the top-ranked open source models from the LMSys Chatbot Arena's overall leaderboard, ensuring you always have access to the most capable AI for a wide range of tasks.

Sep 9
$3.03/M input tokens$3.82/M output tokens

A mix that picks the highest-ranked model for Russian prompts, based on LMSYS Russian Leaderboard.

Oct 10
$4.99/M input tokens$17.20/M output tokens

A mix that picks the highest-ranked model for Russian prompts, based on LMSYS Russian Leaderboard.

Oct 10
$3.29/M input tokens$5.10/M output tokens

A mix that picks the highest-ranked model for Spanish prompts, based on LMSYS Spanish Leaderboard.

Oct 10
$4.20/M input tokens$13.23/M output tokens

A mix that picks the highest-ranked model for Spanish prompts, based on LMSYS Spanish Leaderboard.

Oct 10
$1.70/M input tokens$1.70/M output tokens

A mix that picks the highest-ranked model for prompts with image attachments, based on LMSYS Vision Leaderboard.

Oct 10
$4.94/M input tokens$14.81/M output tokens

A Mixture-of-Agents (MoA) synthesis mix optimized for fast and balanced chat use cases. This mix leverages multiple 'proposer' models, including Llama 3.1 70B on Groq and DeepSeek v2.5, with an 'aggregation' model that synthesizes their outputs.

Oct 21
$0.46/M input tokens$0.64/M output tokens

A custom-built Mixture-of-Agents (MoA) synthesis mix optimized for challenging coding tasks. This mix leverages multiple 'proposer' models, including Claude 3.5 Sonnet and GPT-4 Turbo, with an 'aggregation' model that synthesizes their outputs. In benchmarks, it demonstrated 28% better performance compared to Claude 3.5 Sonnet alone, particularly excelling at complex programming challenges.

Aug 26
$6.00/M input tokens$20.00/M output tokens

A fast variant of the Coding Mixture of Agents (MoA) that uses GPT-4o-mini to classify task difficulty. Simple tasks are quickly processed by GPT-4o, while complex ones utilize the full MoA. With 68% classification accuracy and a bias towards the MoA when uncertain, this mix optimizes for speed without compromising on quality for challenging problems.

Oct 1
$6.20/M input tokens$19.10/M output tokens

An open-source Mixture-of-Agents (MoA) synthesis mix optimized for coding tasks. This mix leverages two 'proposer' models, DeepSeek-2.5 and Mistral Large 2, with Llama 3.1 405B as the 'aggregation' model that synthesizes their outputs. This mix offers a powerful, cost-effective solution for complex programming challenges.

Oct 1
$3.23/M input tokens$9.63/M output tokens

A mix that picks the highest-ranked model for Spanish prompts, based on Scale's Multilingual Prompts Dataset aimed at measuring a model's proficiency in engaging with Spanish users from Spain, Mexico and the rest of Latin America, reflecting complexity of global communication.

Aug 13
$6.12/M input tokens$18.36/M output tokens

Get Your Own Custom Mixes

Submit your use case or a general description of what you need for a custom tuned solution.