Jamba Instruct
ai21.jamba-instruct-v1:0Pricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.50 | $0.70 |
What it costs a month
At Amazon Bedrock list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$203
- RAG over documents2,000 requests a day, 8K in / 0.6K out$265
- Coding agent1,000 requests a day, 40K in / 2K out$642
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,368
Where to run it
2 hosts serve Jamba Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Amazon BedrockCloud ai21.jamba-instruct-v1:0 | $0.50 / $0.70 | ai21.jamba-instruct-v1:0 | |
SnowflakeCloud jamba-instruct | - | jamba-instruct |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Jamba Open Model LicenseRuntimes: vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Amazon Bedrock.
Smaller AI21 Labs models
No cheaper AI21 Labs model keeps its key capabilities.
Other frontier labs
- 16% less
- 64% less
- 64% less
- 52% less
Open-weight picks
- 5% less
- 5% less
- 12% less
- 18% less
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/ai21.jamba-instruct-v1:0",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Jamba Instruct cost?
On Amazon Bedrock, Jamba Instruct costs $0.50 per million input tokens and $0.70 per million output tokens.
Which APIs offer Jamba Instruct?
Jamba Instruct runs on 2 APIs: Amazon Bedrock and Snowflake.
What is Jamba Instruct's context window?
70K tokens, with up to 4K tokens in one reply.
Is Jamba Instruct being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Jamba Instruct?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (16% less), Claude Haiku 5.5 on Anthropic (64% less) and DeepSeek Flash on DeepSeek (5% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Jamba Instruct's API model id?
Use ai21.jamba-instruct-v1:0 with Amazon Bedrock. Other hosts use their own ids: jamba-instruct on Snowflake.
Sources
Raw catalog entry for ai21.jamba-instruct-v1:0 on Amazon Bedrock
{
"input_cost_per_token": 5e-7,
"litellm_provider": "bedrock",
"max_input_tokens": 70000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7e-7,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_system_messages": true
}