Venice Models

通过 uv 运行 Python 脚本，调用 Venice AI 公开的模型目录接口，按文本、图像、视频、TTS、ASR、嵌入、代码等类型筛选模型，并以表格、JSON 或名称列表展示模型 ID、上下文与价格信息，可选保存为文件。无需 API Key。

sabrinaaquino

热度 51.47

最近更新 2026-03-14 12:25:25

分类：搜索依赖：代码执行 / 第三方 API / 读写文件应用场景：研究 / 推荐

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add venice-models

Metadata

name: venice-models
description: Explore Venice AI's available models - LLMs, image generators, video, TTS, ASR, and embeddings. View capabilities, pricing, and constraints.
homepage: https://venice.ai
metadata: {"openclaw":{"emoji":"🔍","requires":{"bins":["uv"]},"install":[{"id":"uv-brew","kind":"brew","formula":"uv","bins":["uv"],"label":"Install uv (brew)"}]}}

Venice Models

Explore Venice AI's available models - discover capabilities, pricing, and find the right model for your use case.

API Base URL: https://api.venice.ai/api/v1 No API key required - the models endpoint is public.

List Models

uv run {baseDir}/scripts/models.py

Options:

--type: Filter by model type (default: all)
- all - All models
- text - LLMs for chat/completions
- image - Image generation
- video - Video generation
- tts - Text-to-speech
- asr - Speech recognition
- embedding - Text embeddings
- code - Code-optimized LLMs
--format: Output format: table, json, names (default: table)
--output: Save to file

Examples

List all models:

uv run {baseDir}/scripts/models.py

Image generation models only:

uv run {baseDir}/scripts/models.py --type image

Video models:

uv run {baseDir}/scripts/models.py --type video

Just model names (for scripting):

uv run {baseDir}/scripts/models.py --type text --format names

Export to JSON:

uv run {baseDir}/scripts/models.py --format json --output models.json

Model Types

Type	Description
`text`	LLMs for chat, completions, reasoning
`image`	Image generation (Flux, SDXL, etc.)
`video`	Video generation
`tts`	Text-to-speech voices
`asr`	Automatic speech recognition (Whisper)
`embedding`	Text embeddings for RAG
`code`	Code-optimized LLMs
`upscale`	Image upscaling

Output Formats

Table (default):

MODEL ID                    TYPE    CONTEXT  PRICING
llama-3.3-70b              text    128K     $0.35/M in, $0.40/M out
flux-2-max                 image   -        $0.03/image
openai/whisper-large-v3    asr     -        $0.006/minute

Names only:

llama-3.3-70b
flux-2-max
openai/whisper-large-v3

Runtime Note

This skill uses uv run which automatically installs Python dependencies (httpx) via PEP 723 inline script metadata. No manual Python package installation required - uv handles everything.

API Reference

Endpoint	Description	Auth
`GET /models`	List all models	None (public)
`GET /models?type=image`	Filter by type	None
`GET /models/traits`	Model capabilities	None

Full API docs: docs.venice.ai