Last refreshed 2026-05-05. Next refresh: weekly.
Why use Mistral Medium 3 Instruct on NVIDIA NIM?
NVIDIA NIM offers Mistral Medium 3 Instruct with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Mistral Medium 3 Instruct 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: mistralai/mistral-medium-3-instructmistralai/mistral-medium-3-instructRequest example
mistralai/mistral-medium-3-instruct.Gotchas
- Use provider model ID "mistralai/mistral-medium-3-instruct", not the LLMReference slug "mistral-medium-3-instruct".
Compare Mistral Medium 3 Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| Mistral AI Studio | $0.40 | $2.00 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
Capabilities
No model capability flags are currently sourced.
About Mistral Medium 3 Instruct
Mistral Medium 3, a mid-size instruction-tuned model from Mistral AI.
FAQ
What is the context window for Mistral Medium 3 Instruct on NVIDIA NIM?
Mistral Medium 3 Instruct supports a 128,000 token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other Mistral Medium 3 Instruct providers?
Mistral Medium 3 Instruct is available from 2 providers. The cheapest input pricing is $0.40/1M tokens from Mistral AI Studio.
What API model ID do I use for Mistral Medium 3 Instruct on NVIDIA NIM?
Use the model ID mistralai/mistral-medium-3-instruct when calling NVIDIA NIM's API.
Who created Mistral Medium 3 Instruct?
Mistral Medium 3 Instruct was created by MistralAI as part of the Mistral Medium model family.
Is Mistral Medium 3 Instruct open source?
Mistral Medium 3 Instruct is open source according to the seed data.