Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for eva-unit-01

EVA-UNIT-01

Access 4 EVA-UNIT-01 models through the OpenRouter unified API including EVA Llama 3.33 70B, EVA Qwen2.5 72B, and EVA Qwen2.5 32B. Compare pricing, context windows, benchmarks, and capabilities between different EVA-UNIT-01 models.

EVA-UNIT-01 requests made on OpenRouter

Not enough data to display yet.

  • Favicon for eva-unit-01
    EVA Llama 3.33 70BEVA Llama 3.33 70B

    EVA Llama 3.33 70b is a roleplay and storywriting specialist model. It is a full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model This model was built with Llama by Meta.

    by eva-unit-01Dec 16, 202416K context
  • Favicon for eva-unit-01
    EVA Qwen2.5 72BEVA Qwen2.5 72B

    EVA Qwen2.5 72B is a roleplay and storywriting specialist model. It's a full-parameter finetune of Qwen2.5-72B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model.

    by eva-unit-01Nov 21, 202432K context
  • Favicon for eva-unit-01
    EVA Qwen2.5 32BEVA Qwen2.5 32B

    EVA Qwen2.5 32B is a roleplaying/storywriting specialist model. It's a full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model.

    by eva-unit-01Nov 8, 202432K context
  • Favicon for eva-unit-01
    EVA Qwen2.5 14BEVA Qwen2.5 14B

    A model specializing in RP and creative writing, this model is based on Qwen2.5-14B, fine-tuned with a mixture of synthetic and natural data. It is trained on 1.5M tokens of role-play data, and fine-tuned on 1.5M tokens of synthetic data.

    by eva-unit-01Sep 30, 202433K context

Frequently asked questions

OpenRouter serves 4 EVA-UNIT-01 models behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as eva-unit-01/eva-llama-3.33-70b. The quickstart has request examples for every supported SDK.

EVA Qwen2.5 14B has the largest context window of any EVA-UNIT-01 model on OpenRouter, accepting up to 32,768 tokens per request.

EVA Llama 3.33 70B is the most recently added EVA-UNIT-01 model on OpenRouter, listed on December 16, 2024.