Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add 0xatd/cheaptokens-skills --skill venice-image-generategit clone --depth 1 https://github.com/0xatd/cheaptokens-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-image-generate)<a href="https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-image-generate"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/venice-image-generate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-image-generate"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/venice-image-generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02438 |
| Opus 5 | $0.00036 | $0.01219 |
| Sonnet 5 | $0.00015 | $0.00488 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade B, and why
venice-image-generate scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const res = await fetch('https://api.venice.ai/api/v1/image/generate', { method: 'POST', Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://api.venice.ai/api/v1/image/generate \ This is a copy
91% identical to venice-image-generate — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venice Image Generation
Two text-to-image endpoints:
POST /api/v1/image/generate— Venice-native, full control (negative prompts, CFG, seed, up to 4 variants).POST /api/v1/images/generations— OpenAI-compatible, fewer knobs but drop-in for the OpenAI SDK.
Plus:
GET /api/v1/image/styles— list of style preset names forstyle_preset.
For editing / upscaling / multi-image / background removal, see venice-image-edit.
Use when
- You need to generate images from text prompts.
- You need multiple variants in one call.
- You're porting from OpenAI's
images.generateand want a zero-change SDK swap. - You want to browse style presets before committing to one.
/image/generate — Venice-native
Request
curl https://api.venice.ai/api/v1/image/generate \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-image-turbo",
"prompt": "A beautiful sunset over a mountain range",
"width": 1024,
"height": 1024,
"cfg_scale": 7.5,
"steps": 8,
"seed": 123456789,
"variants": 1,
"format": "webp",
"style_preset": "3D Model",
"safe_mode": true
}'
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
model |
string | — | Required. Image model ID. GET /models?type=image. |
prompt |
string | — | Required. Max promptCharacterLimit from the model's model_spec.constraints (typically 1500–7500). |
negative_prompt |
string | — | Describe what not to show. Same character cap as prompt. |
width, height |
int | 1024, 1024 | ≤ 1280 each. Must be divisible by constraints.widthHeightDivisor on the model's model_spec. |
aspect_ratio |
string | — | "1:1", "16:9", "9:16", … — used by models like Nano Banana instead of width/height. |
resolution |
string | — | "1K", "2K", "4K" — used by resolution-driven models. |
cfg_scale |
number | model default | 0 < x ≤ 20. Higher = more prompt adherence. |
steps |
int | 8 | Inference steps. Some models ignore it (e.g. Turbo). |
seed |
int | 0 | -999999999..999999999. Use 0/omit for random. |
variants |
int | 1 | 1–4. Only if return_binary: false. |
lora_strength |
int | — | 0–100 when model uses Loras. |
style_preset |
string | — | Value from GET /image/styles. |
format |
"webp"/"png"/"jpeg" |
webp |
Response image format. |
return_binary |
bool | false |
true → binary image/* response; false → JSON with base64. |
embed_exif_metadata |
bool | false |
Embed prompt info in EXIF. |
hide_watermark |
bool | false |
Venice may still watermark certain content. |
safe_mode |
bool | true |
Blurs adult content. |
enable_web_search |
bool | false |
Only some models. Charges extra. |
inpaint |
— | — | Deprecated since May 19 2025. A new inpaint API is forthcoming. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 211 lines · 73 tokens per session scan B 8b76b3a4b3b0
venice-image-generate is a skill published in the GitHub repository 0xatd/cheaptokens-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,438 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 91% identical to venice-image-generate, differing in 28 lines, and is treated as a copy.
Other skills, from other repositories
image-prompting
Use when generating or editing images via blockrunimage — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts that actually render…
openai-compatible-imagegen
Generate, edit, and batch-process images through the bundled script and configured API Key provider (OpenAI-compatible or Atlas Cloud). Use for photos, illustrations, product visuals, posters, covers, diagrams, UI references, game art, transparent subjects, reference-image edits, inpainting, multi-reference…
storyboard-to-video
Turn a single N-frame storyboard image (e.g. a 3x3 grid) into a multi-shot AI video with seamless cuts, paid per-call through taskfuel.ai/x402. Use when the user has a storyboard/grid image and wants it animated, wants a storyboard generated from scratch and then animated, mentions "storyboard to video", or wants…
build-brand-system
Create a brand identity from a product brief — pick a visual direction, write the spec (palette, type, logo, voice, usage rules), and generate one 3x3 board that shows the system in use, paid per-call through taskfuel.ai. Use when the user wants a brand, visual identity, style guide, brand system, design language, or…
worldclaw-openworld
Agentic coarse-to-fine blueprint for generating large-scale, explorable, editable 3D open-world scenes from a single open-ended text prompt — derived from Tencent Hunyuan's WorldClaw (arXiv 2608.05248, Guo/Li/Li/Huang, 2026). Use whenever a project needs to generate a whole 3D world / open-world scene / large terrain…
bridgenode
BridgeNode MCP wrapper — stdio MCP server proxying to remote streamable-HTTP endpoint with automatic x402 payment on Solana USDC. No API keys. Use when an agent needs LLM inference through MCP (Claude Code, Cursor, etc.) and has no provider API key.