Overview
Provider Type
APIAPI Endpoint
https://us-south.ml.cloud.ibm.com/ml/v1/text/chat?version=2025-02-11
Free Tier Highlights
Why Choose IBM watsonx.ai (Lite plan)?
IBM watsonx.ai (Lite plan) stands out for its unique features and capabilities. With a developer-friendly API and comprehensive documentation, you can integrate AI capabilities into your applications within minutes.
Quick Start Guide
Create an IBM Cloud account and a watsonx.ai Runtime Lite instance plus a project
create an IBM Cloud API key and exchange it for an IAM token
POST to /ml/v1/text/chat with model_id and project_id
Available Models
| Model Name | ID | Context | Capabilities | |
|---|---|---|---|---|
| Granite 4 H Small Free |
ibm/granite-4-h-small
|
131 000 Context |
- | |
| Llama 3.3 70B Instruct Free |
meta-llama/llama-3-3-70b-instruct
|
131 000 Context |
- | |
| Llama 4 Maverick Free |
meta-llama/llama-4-maverick-17b-128e-instruct-fp8
|
131 000 Context |
- | |
| GPT-OSS 120B Free |
openai/gpt-oss-120b
|
131 000 Context |
- | |
| Mistral Small 3.1 24B Free |
mistralai/mistral-small-3-1-24b-instruct-2503
|
128 000 Context |
- |
Free Tier Pricing & Limits
Rate Limit
Requests per minute
Daily Quota
Requests per day
Use Cases
Enterprise PoCs on IBM Cloud
testing Granite models
Limitations & Considerations
IBM Cloud signup asks for a credit card for identity verification
not OpenAI-compatible (IAM tokens, project_id)
one Lite instance per account, no quota increase
Community Hub
LiveJoin the discussion, share tips, and rate IBM watsonx.ai (Lite plan).
Quick Reactions
Add Discussion
Comments are moderated. Be helpful and respectful.