Crosshatch mixes combine responses from top AI language models for developers.

Coding Mixture of Agents

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.

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

LMSys Overall Leaderboard

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.

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

Crosshatch Chat

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.

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

Improve Response Quality

Combine multiple top-tier AI models simultaneously using our Synthesis Mixes. This approach often outperforms single-model solutions for complex tasks.

Our coding mix showed an 30% improvement over Claude 3.5 Sonnet on coding benchmarks.

Synthesize
Future proof

Future-Proof your App

Focus on development, not model choice. Crosshatch automatically selects the top-performing model for each task, leveraging up-to-date benchmarks from respected sources such as LMSys and Scale.ai.

Integrate in Minutes

Crosshatch is compatible with OpenAI’s API. Just replace a few lines of code to get started and give your app access to top-tier models.

Integrate