agentleFS
0xatd0xatd/cheaptokens-skills/skills/venice-api-keys/SKILL.md

venice-api-keys

Skill2 starsChanged 5 months agoMITView on GitHub

Manage Venice API keys. Covers GET/POST/PATCH/DELETE /api_keys, GET /api_keys/{id}, GET /api_keys/rate_limits, GET /api_keys/rate_limits/log, the two-step /api_keys/generate_web3_key wallet flow, INFERENCE vs ADMIN key types, and per-key consumption limits (USD / DIEM).

  • Reads credentials
  • Sends data out

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Only description, expiresAt, and consumptionLimit are mutable.

    line 115

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

EndpointPurpose
GET /api_keysList your keys (masked).
POST /api_keysCreate a new key. Response contains the only copy of the secret.
PATCH /api_keysUpdate 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_limitsBalances + per-model rate-limit tiers for the current key.
GET /api_keys/rate_limits/logLast 50 rate-limit breaches.
GET /api_keys/generate_web3_keyGet a SIWE-style token to sign with a wallet.
POST /api_keys/generate_web3_keyAuthenticate 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

TypeCan call
INFERENCEInference 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.
ADMINEverything 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" } }
    }
  ]
}

The full secret is never returned on list — only last6Chars.

POST /api_keys — create

curl https://api.venice.ai/api/v1/api_keys \
  -H "Authorization: Bearer $ADMIN_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "apiKeyType": "INFERENCE",
    "description": "backend prod",
    "expiresAt": "2026-12-31T23:59:59Z",
    "consumptionLimit": { "usd": 50, "diem": 10 }
  }'

Response includes the one-time apiKey secret:

{
  "success": true,
  "data": {
    "id": "uuid",
    "apiKey": "VENICE_INFERENCE_KEY_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "apiKeyType": "INFERENCE",
    "description": "backend prod",
    "expiresAt": "2026-12-31T23:59:59Z",
    "consumptionLimit": { "usd": 50, "diem": 10 }
  }
}

Save it immediately — Venice won't show the secret again. If you lose it, delete and re-create.

Required

  • apiKeyType
  • description

Optional

  • expiresAt — empty string or ISO 8601 date/datetime. Omit for non-expiring.
  • consumptionLimit.usd / .diem — per-epoch caps. Null means no cap on that currency.
  • consumptionLimit.vcu — deprecated (legacy Diem). Use diem instead.

PATCH /api_keys — update

curl -X PATCH https://api.venice.ai/api/v1/api_keys \
  -H "Authorization: Bearer $ADMIN_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "id": "uuid", "description": "renamed", "consumptionLimit": { "usd": 100 } }'

Only description, expiresAt, and consumptionLimit are mutable. Pass "expiresAt": "" or null to remove an expiration.

DELETE /api_keys?id=<uuid> — revoke

curl -X DELETE "https://api.venice.ai/api/v1/api_keys?id=uuid" \
  -H "Authorization: Bearer $ADMIN_KEY"

Returns {"success": true}. Revocation is immediate.

GET /api_keys/{id} — details

Returns one key's full metadata plus trailing-7-day usage. Useful for an admin dashboard row view.

GET /api_keys/rate_limits

curl https://api.venice.ai/api/v1/api_keys/rate_limits \
  -H "Authorization: Bearer $VENICE_API_KEY"

Returns for the calling key:

{
  "data": {
    "accessPermitted": true,
    "apiTier": { "id": "paid", "isCharged": true },
    "balances": { "USD": 50.23, "DIEM": 100.023 },
    "keyExpiration": "2025-06-01T00:00:00Z",
    "nextEpochBegins": "2025-05-07T00:00:00.000Z",
    "rateLimits": [
      {
        "apiModelId": "zai-org-glm-5-1",
        "rateLimits": [
          { "type": "RPM", "amount": 100 },
          { "type": "TPM", "amount": 200000 },
          { "type": "RPD", "amount": 10000 }
        ]
      }
    ]
  }
}

Use it to:

  • Display current balances in-app.
  • Warm-gate calls when the relevant model's RPM cap is near.
  • Know when the next epoch resets (DIEM, bundled credits).

GET /api_keys/rate_limits/log

Returns the last 50 rate-limit breaches. Response is wrapped as { object: "list", data: [...] }:

{
  "object": "list",
  "data": [
    { "apiKeyId": "...", "modelId": "zai-org-glm-5-1", "rateLimitType": "RPM",
      "rateLimitTier": "paid", "timestamp": "2026-04-20T12:34:56Z" }
  ]
}

Feed these into your monitoring when tuning concurrency.

Web3 API keys — two-step wallet flow

Lets a wallet that holds sVVV mint a classic Bearer API key. No Venice account required.

1. GET /api_keys/generate_web3_key

curl https://api.venice.ai/api/v1/api_keys/generate_web3_key

Returns { success: true, data: { token: "<jwt-ish token>" } }.

2. Sign the token with your wallet, then POST /api_keys/generate_web3_key

import { Wallet } from 'ethers'

const { data: { token } } = await fetch(`${base}/api_keys/generate_web3_key`).then(r => r.json())
const wallet = new Wallet(process.env.WALLET_KEY!)
const signature = await wallet.signMessage(token)

const res = await fetch(`${base}/api_keys/generate_web3_key`, {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    apiKeyType: 'INFERENCE',
    description: 'Web3 API Key',
    address: wallet.address,
    signature,
    token,
    consumptionLimit: { usd: 50 },
  }),
})

const { data } = await res.json()
console.log(data.apiKey) // save this once

The returned apiKey behaves exactly like a normal Bearer key.

Recipes

Per-customer keys with $5 USD limit

await fetch(`${base}/api_keys`, {
  method: 'POST',
  headers: { Authorization: `Bearer ${ADMIN_KEY}`, 'Content-Type': 'application/json' },
  body: JSON.stringify({
    apiKeyType: 'INFERENCE',
    description: `cust:${customerId}`,
    consumptionLimit: { usd: 5 },
  }),
})

Rotate monthly; revoke on churn.

Health-check for a key

const { data } = await fetch(`${base}/api_keys/rate_limits`, {
  headers: { Authorization: `Bearer ${key}` },
}).then(r => r.json())

if (!data.accessPermitted) alert('Key blocked — top up or change tier')

Errors

CodeMeaning
400Bad body (e.g. missing apiKeyType, malformed expiresAt), or attempting to create when you already have 500 active keys.
401Missing / bad / non-admin key for admin-only routes.
429Exceeded 20 creates/min.
500Transient; retry.

Gotchas

  • The secret is returned exactly once, in the POST response. Losing it = delete + recreate.
  • consumptionLimit is per epoch (day / reset cycle), not per call.
  • INFERENCE keys can't call admin-only routes (POST/PATCH/DELETE /api_keys, GET /api_keys, GET /api_keys/{id}, GET /billing/balance, GET /billing/usage). They can call GET /api_keys/rate_limits and /api_keys/rate_limits/log for themselves. Use a separate ADMIN key for management.
  • vcu is legacy — use diem.
  • expiresAt of empty string "" means "no expiration" in CREATE; on UPDATE it removes an existing one.
  • Rate-limit log is capped at 50 entries — pull it frequently if debugging bursts.
  • The Web3 key flow requires wallet holdings of sVVV; otherwise the signing step is rejected.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.