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-api-keysgit 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-api-keys)<a href="https://agentmods.dev/skills/0xatd/cheaptokens-skills/venice-api-keys"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/venice-api-keys/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-api-keys"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/venice-api-keys.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 | $0.00079 | $0.02535 |
| Opus 5 | $0.00039 | $0.01267 |
| Sonnet 5 | $0.00016 | $0.00507 |
| Haiku 4.5 | $0.00008 | $0.00253 |
Grade A, and why
venice-api-keys scanned grade A with 1 finding 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 10d 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.
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/api_keys \ This is a copy
100% identical to venice-api-keys — 0 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venice API Keys
Admin endpoints for managing Bearer API keys. You need an ADMIN key (or parent session) to call these. For wallet-only auth, use venice-auth / venice-x402 instead.
| Endpoint | Purpose |
|---|---|
GET /api_keys |
List your keys (masked). |
POST /api_keys |
Create a new key. Response contains the only copy of the secret. |
PATCH /api_keys |
Update description, expiresAt, consumptionLimit. |
DELETE /api_keys?id=... |
Revoke a key. |
GET /api_keys/{id} |
Full details for one key (usage, limits, expiration). |
GET /api_keys/rate_limits |
Balances + per-model rate-limit tiers for the current key. |
GET /api_keys/rate_limits/log |
Last 50 rate-limit breaches. |
GET /api_keys/generate_web3_key |
Get a SIWE-style token to sign with a wallet. |
POST /api_keys/generate_web3_key |
Authenticate a wallet (holds sVVV) and mint a classic API key. |
Limits: key creation is capped at 20 requests/minute and 500 active keys per user.
Key types
| Type | Can call |
|---|---|
INFERENCE |
Inference endpoints plus any route that only requires authentication — e.g. /chat/*, /image/*, /audio/*, /video/*, /embeddings, /augment/*, /crypto/rpc, /characters, /api_keys/rate_limits*, /support-bot. Rejected from admin routes listed below with 401. |
ADMIN |
Everything an INFERENCE key can do, plus admin-only routes: POST/PATCH/DELETE /api_keys, GET /api_keys (list), GET /api_keys/{id}, GET /billing/balance, GET /billing/usage. |
A leaf app should almost always use INFERENCE keys — per-app, per-user, with consumption caps.
GET /api_keys
curl https://api.venice.ai/api/v1/api_keys \
-H "Authorization: Bearer $ADMIN_KEY"
Returns:
{
"object": "list",
"data": [
{
"id": "uuid",
"apiKeyType": "INFERENCE",
"description": "backend prod",
"createdAt": "2025-10-01T12:00:00Z",
"expiresAt": null,
"lastUsedAt": "2026-04-20T10:05:00Z",
"last6Chars": "2V2jNW",
"consumptionLimits": { "usd": 50, "diem": 10 },
"usage": { "trailingSevenDays": { "usd": "4.20", "diem": "0.00" } }
}
]
}
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.
- 10d ago First seen · 269 lines · 79 tokens per session scan A e84fd012564e
venice-api-keys is a skill published in the GitHub repository 0xatd/cheaptokens-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,535 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to venice-api-keys, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
t2000-sui-platform
Sui platform patterns for throughput and gas — Address Balances (SIP-58) accumulators that let ONE address run concurrent txs, and gasless stablecoin transfers that remove the "you need SUI to send USDC" wall. Includes the eligibility gotchas that cause misleading failures (0.01 minimum, the dust-remainder floor…
x402-server
Add x402 payment protection to any API endpoint using @dexterai/x402/server. Trigger when the user wants to monetize an API, add a paywall, accept crypto payments on their server, set up Stripe settlement, configure dynamic pricing, create access passes, or enable sponsored access (ads for agents).
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.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
web3-fullstack-packaged-build
Systematic full-stack Web3 build with mandatory packaging and delivery phase.
solana-dev
Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my Solana program", "deploy to devnet", "send a v1 transaction", "support larger transactions", "fix maxSupportedTransactionVersion", or "explain…