Skip to main content

Text Models

Model NameModel IDPrice (in/out)Context LimitCapabilitiesTraits
Venice Uncensored 1.1venice-uncensored$0.20 / $0.9032,768most_uncensored
Venice Smallqwen3-4b$0.05 / $0.1540,960Function Calling, Reasoning
Venice Medium (3.1)mistral-31-24b$0.50 / $2.00131,072Function Calling, Visiondefault_vision
Venice Large 1.1qwen3-235b$0.90 / $4.50131,072Function Calling, Reasoning
Llama 3.2 3Bllama-3.2-3b$0.15 / $0.60131,072Function Callingfastest
Llama 3.3 70Bllama-3.3-70b$0.70 / $2.8065,536Function Callingdefault, function_calling_default
Pricing is per 1M tokens (input / output). Models with reasoning capabilities support advanced reasoning via thinking mode. qwen3-235b Venice Large 1.1 - Most powerful flagship model
mistral-31-24b Venice Medium (3.1) - Vision + function calling
qwen3-4b Venice Small - Fast, affordable for most tasks
llama-3.3-70b Llama 3.3 70B - Balanced high-performance model

Text Model Categories

Reasoning Models qwen3-235b Venice Large 1.1 - Advanced reasoning capabilities
qwen3-4b Venice Small - Efficient reasoning model
Vision-Capable Models mistral-31-24b Venice Medium (3.1) - Vision-capable model Cost-Optimized Models qwen3-4b Venice Small - Best balance of speed and cost
llama-3.2-3b Llama 3.2 3B - Fastest for simple tasks
Uncensored Models venice-uncensored Venice Uncensored 1.1 - No content filtering High-Intelligence Models llama-3.3-70b Llama 3.3 70B - Balanced high-intelligence
qwen3-235b Venice Large 1.1 - Most powerful flagship model

Beta Models

Model NameModel IDPrice (in/out)Context LimitCapabilitiesTraits
Qwen 3 Next 80Bqwen3-next-80b$0.35 / $1.90262,144Function Calling
Qwen 3 Coder 480Bqwen3-coder-480b-a35b-instruct$0.75 / $3.00262,144Function Calling
Hermes 3 Llama 3.1 405Bhermes-3-llama-3.1-405b$1.10 / $3.00131,072
Beta models are experimental and not recommended for production use. These models may be changed, removed, or replaced at any time without notice. Use them for testing and evaluation purposes only. For production applications, use the stable models listed above.

Image Models

Model NameModel IDPriceModel SourceTraits
Venice SD35venice-sd35$0.01Stable Diffusion 3.5 Largedefault, eliza-default
HiDreamhidream$0.01HiDream I1 Dev
Qwen Imageqwen-image$0.01Qwen Image
FLUX Standard (D)flux-dev$0.01FLUX.1 Devhighest_quality
FLUX Custom (D)flux-dev-uncensored$0.01FLUX.1 Dev
Lustify SDXLlustify-sdxl$0.01Lustify SDXL
Anime (WAI)wai-Illustrious$0.01WAI-Illustrious
qwen-image Qwen Image - Highest quality image generation
venice-sd35 Venice SD35 - Default choice with Eliza integration
lustify-sdxl Lustify SDXL - Uncensored image generation
hidream HiDream - Production-ready generation

Image Model Categories

High-Quality Models qwen-image Qwen Image - Highest quality output
hidream HiDream - Production-ready generation
Default Models venice-sd35 Venice SD35 - Default choice, Eliza-optimized Special Purpose Models lustify-sdxl Lustify SDXL - Adult content generation
wai-Illustrious Anime (WAI) - Anime-style generation

Audio Models

Text-to-Speech Models

tts-kokoro Kokoro TTS - 60+ multilingual voices for natural speech
Model NameModel IDPriceVoices AvailableModel Source
Kokoro Text to Speechtts-kokoro$3.50 per 1M chars60+ voicesKokoro-82M
The tts-kokoro model supports a wide range of multilingual and stylistic voices (including af_nova, am_liam, bf_emma, zf_xiaobei, and jm_kumo). Voice is selected using the voice parameter in the request payload.

Embedding Models

text-embedding-bge-m3 BGE-M3 - Versatile embedding model for text similarity
Model NameModel IDPriceModel Source
BGE-M3text-embedding-bge-m3$0.15 / $0.60 per 1M tokensKimChen/bge-m3-GGUF

Image Processing Models

upscaler Image Upscaler - Enhance image resolution up to 4x
qwen-image Qwen Image - Multimodal image editing model

Image Upscaler

Model NameModel IDPriceUpscale Options
Upscalerupscaler$0.012x ($0.02), 4x ($0.08)

Image Editing (Inpaint)

Model NameModel IDPriceModel SourceTraits
Qwen Imageqwen-image$0.04Qwen Imagespecialized_editing

Model Features

  • Vision: Ability to process and understand images
  • Reasoning: Advanced logical reasoning capabilities
  • Function Calling: Support for calling external functions and tools
  • Traits: Special characteristics or optimizations (e.g., fastest, most_intelligent, most_uncensored)

Usage Notes

  • Input pricing refers to tokens sent to the model
  • Output pricing refers to tokens generated by the model
  • Context limits define the maximum number of tokens the model can process in a single request
  • (D) Scheduled for deprecation. For timelines and migration guidance, see the Deprecation Tracker.
I