Last refreshed 2026-05-14. Next refresh: weekly.
Why use Magistral Small 2506 on NVIDIA NIM?
NVIDIA NIM offers Magistral Small 2506 with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: mistralai/magistral-small-2506Model ID
mistralai/magistral-small-2506Request example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
mistralai/magistral-small-2506.Gotchas
- Use provider model ID "mistralai/magistral-small-2506", not the LLMReference slug "magistral-small-2506".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
Capabilities
Reasoning
About Magistral Small 2506
Mistral Magistral Small reasoning model released January 2026.
FAQ
What is the context window for Magistral Small 2506 on NVIDIA NIM?
Magistral Small 2506 supports a 128,000 token context window on NVIDIA NIM.
What API model ID do I use for Magistral Small 2506 on NVIDIA NIM?
Use the model ID mistralai/magistral-small-2506 when calling NVIDIA NIM's API.
Who created Magistral Small 2506?
Magistral Small 2506 was created by MistralAI as part of the Magistral model family.
Is Magistral Small 2506 open source?
Magistral Small 2506 is open source according to the seed data.
Model Specs
Released2025-06-10
Context128K
ArchitectureDecoder Only