invokeable()
← directory / providers / ai21

AI21 Studio

first-party
2
models served
AI21_API_KEY
auth
api.ai21.com/studio/v1
base url

OpenAI-compatible chat completions. Serves the Jamba family (hybrid SSM-Transformer, 256K context). Aliases like jamba-mini point at the latest dated snapshot. docs →

01Request template

Every model below is invoked with this shape — swap in the provider model ID from the table.

shell · template
curl https://api.ai21.com/studio/v1/chat/completions \
  -H "Authorization: Bearer $AI21_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "{{MODEL_ID}}",
    "messages": [{"role": "user", "content": "Hello, world"}]
  }'

02Models served · newest first

ModelProvider model IDIn $/MOut $/MContext
Jamba Large 1.7AI21 Labs jamba-large-1.7 2.00 8.00 262K
Jamba Mini 2AI21 Labs jamba-mini-2 0.20 0.40 262K