Last refreshed 2026-05-14. Next refresh: weekly.
Why use Mistral Small 4 on NVIDIA NIM?
NVIDIA NIM offers Mistral Small 4 with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Mistral Small 4 across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: mistralai/mistral-small-4-119b-2603mistralai/mistral-small-4-119b-2603Request example
mistralai/mistral-small-4-119b-2603.Gotchas
- Use provider model ID "mistralai/mistral-small-4-119b-2603", not the LLMReference slug "mistral-small-4".
Compare Mistral Small 4 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.15 | $0.60 |
| NVIDIA NIM | — | — |
| Mistral AI Studio | $0.15 | $0.60 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
About Mistral Small 4
Mistral Small 4 is a hybrid 119B MoE model unifying instruct, reasoning, and coding capabilities. Features configurable reasoning effort per request and native function calling with JSON output support.
FAQ
What is the context window for Mistral Small 4 on NVIDIA NIM?
Mistral Small 4 supports a 256,000 token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other Mistral Small 4 providers?
Mistral Small 4 is available from 3 providers. The cheapest input pricing is $0.15/1M tokens from OpenRouter.
What API model ID do I use for Mistral Small 4 on NVIDIA NIM?
Use the model ID mistralai/mistral-small-4-119b-2603 when calling NVIDIA NIM's API.
Who created Mistral Small 4?
Mistral Small 4 was created by MistralAI as part of the Mistral Small model family.
Is Mistral Small 4 open source?
Mistral Small 4 is open source under Apache 2.0 according to the seed data.