Jamba Instruct API Pricing
As of October 10, 2026, Jamba Instruct costs $0.50 per 1M input tokens and $0.70 per 1M output tokens from Azure AI Foundry, the lowest of 3 providers. It has a 70,000-token context window and returns up to 4,096 tokens per response.
azure_ai/jamba-instruct.- Input
- $0.50 / 1M tokens
- Output
- $0.70 / 1M tokens
- Context window
- 70,000 tokens
- Max output
- 4,096 tokens
- Providers
- 3
- Added to LiteLLM
- July 2024
Jamba Instruct pricing by provider
3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Azure AI Foundry | azure_ai/jamba-instruct | $0.50 | $0.70 | 70K |
| Amazon Bedrock | ai21.jamba-instruct-v1:0 | $0.50 | $0.70 | 70K |
| Snowflake Cortex | snowflake/jamba-instruct | – | – | 256K |
What Jamba Instruct costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Azure AI Foundry | $1.35 |
| Amazon Bedrock | $1.35 |
Use Jamba Instruct with LiteLLM
Call Jamba Instruct through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="azure_ai/jamba-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: jamba-instruct
litellm_params:
model: azure_ai/jamba-instruct
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "jamba-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'Jamba Instruct FAQ
How much does Jamba Instruct cost?
Jamba Instruct costs $0.50 per 1M input tokens and $0.70 per 1M output tokens from Azure AI Foundry, the lowest of 3 providers.
What is the context window of Jamba Instruct?
Jamba Instruct has a 70,000-token context window and returns up to 4,096 tokens per response.
Which providers offer Jamba Instruct?
Jamba Instruct is available from 3 providers through LiteLLM: Azure AI Foundry, Amazon Bedrock and Snowflake Cortex.
How do I call Jamba Instruct with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="azure_ai/jamba-instruct", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Jamba Instruct?
Jamba Instruct was added to LiteLLM's model price file in July 2024.
Is Jamba Instruct being deprecated?
Azure AI Foundry deprecated azure_ai/jamba-instruct on March 1, 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models
- aws.amazon.com/bedrock/pricing/
LiteLLM docs: Azure AI Foundry, Amazon Bedrock, Snowflake Cortex.
Provider pages: Azure AI Foundry, Amazon Bedrock, Snowflake Cortex.
