AgentPlayground
Docs
API key errors

The app tries to tell you exactly what went wrong instead of a generic "request failed" — these
are the real messages it shows, grouped by provider and cause.

Anthropic (Claude)
Insufficient Anthropic credits.
Please add credits at console.anthropic.com → Billing.
Or switch to Ollama in the model selector to run models locally for free.

This is the most common one — it's a billing issue, not a bad key. Anthropic requires a funded
account before a key can make requests at all.

Your Anthropic API key appears to be invalid. Go to Settings → API Keys to update it.

The key itself was rejected (typo, revoked, wrong account).

OpenAI / NVIDIA (shared code path)
Your OpenAI API key appears to be invalid. Go to Settings → API Keys to update it.

Same message, with the provider name swapped in — shown on a 401, an "Incorrect API key" response,
or (NVIDIA only) a 403. NVIDIA reports invalid keys with 403 instead of 401, which the app
specifically accounts for so this message still shows correctly there.

No NVIDIA API key found. Get a free one at build.nvidia.com (no
credit card), then add it in Settings → API Keys.

Shown when NVIDIA is selected but no key is configured at all.

{Provider} rate limit exceeded. Please wait a moment and try again.

On a 429 / rate_limit_exceeded response.

Model "{model}" not found. Check your {Provider} model name.

On a 404 / model_not_found — usually a typo'd custom model id typed into the picker's custom-id
field.

Ollama

Ollama errors surface as Ollama stream error: {status} or Ollama complete error: {status}
almost always because the requested model was never actually pulled. See
Ollama not responding for that specifically.

General fallback
No AI provider available. Add an API key in Settings > API Keys (Anthropic, or NVIDIA's free key
from build.nvidia.com), or start Ollama for local models.

Shown when nothing at all is configured — every free-tier fallback (Anthropic → NVIDIA → OpenAI →
Ollama) came up empty.