Last refreshed 2026-05-19. Next refresh: weekly.
Why use Jamba 1.5 Mini on NVIDIA NIM?
NVIDIA NIM offers Jamba 1.5 Mini with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Jamba 1.5 Mini across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: ai21-labs/jamba-1.5-mini-instructai21-labs/jamba-1.5-mini-instructRequest example
ai21-labs/jamba-1.5-mini-instruct.Gotchas
- Use provider model ID "ai21-labs/jamba-1.5-mini-instruct", not the LLMReference slug "jamba-1.5-mini".
Compare Jamba 1.5 Mini Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| AWS Bedrock | $0.20 | $0.40 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
About Jamba 1.5 Mini
Jamba 1.5 Mini is AI21 Labs' Jamba 1.5 model. It offers a 256K-token context window.
FAQ
What is the context window for Jamba 1.5 Mini on NVIDIA NIM?
Jamba 1.5 Mini supports a 256k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other Jamba 1.5 Mini providers?
Jamba 1.5 Mini is available from 2 providers. The cheapest input pricing is $0.20/1M tokens from AWS Bedrock.
What API model ID do I use for Jamba 1.5 Mini on NVIDIA NIM?
Use the model ID ai21-labs/jamba-1.5-mini-instruct when calling NVIDIA NIM's API.
Who created Jamba 1.5 Mini?
Jamba 1.5 Mini was created by AI21 Labs as part of the Jamba 1.5 model family.
Is Jamba 1.5 Mini open source?
Jamba 1.5 Mini has open weights under Jamba Open Model according to the seed data, but that does not necessarily mean an OSI-approved open-source license.