What's free
Lite plan: 300,000 tokens/month for foundation model inference, 20 CUH/month for ML tooling, 100 pages/month of document text extraction
- Credit card
- required
- Phone verification
- not confirmed
- Commercial use
- not confirmed
Free limits
| requests per second | 2 |
|---|---|
| tokens per month | 300,000 |
Lite plan: 2 inference requests per second; 300,000 tokens per month for foundation model inference; not re-read in a plain fetch, figures are those of the entry's own verification. Source: the provider's page, read 2026-10-08.
In the provider's words
2 inference requests per second (explicitly documented for the Lite plan)
The catch
Lite plan doesn't support fine-tuning of foundation or custom models; 1-day idle deployment timeout. Never expires or bills while inside quota, but a payment method (with a nominal ~$1 authorization hold) is required at signup
Free models: not listed yet.
Quickstart — chat completions
from openai import OpenAI
client = OpenAI(base_url="https://us-south.ml.cloud.ibm.com/ml/v1", api_key="<YOUR_FREE_API_KEY>")
resp = client.chat.completions.create(
model="<a-free-model>",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)…or with curl:
curl https://us-south.ml.cloud.ibm.com/ml/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"<a-free-model>","messages":[{"role":"user","content":"Hello!"}]}'Appears in
Compare
Change history
How this free tier has changed since we started tracking it (2026-07-30) — generated from the git history of providers.json.
- 2026-07-30 Updated OpenAI compatibility
- 2026-07-30 Added to the hub