Last refreshed 2026-06-19. Next refresh: weekly.
Why use Mistral Large 3 675B Instruct on NVIDIA NIM?
NVIDIA NIM offers Mistral Large 3 675B Instruct with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Mistral Large 3 675B Instruct across 6 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-large-3-675b-instruct-2512mistralai/mistral-large-3-675b-instruct-2512Request example
mistralai/mistral-large-3-675b-instruct-2512.Gotchas
- Use provider model ID "mistralai/mistral-large-3-675b-instruct-2512", not the LLMReference slug "mistral-large-3".
Compare Mistral Large 3 675B Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.50 | $1.50 |
| AWS Bedrock | $0.50 | $1.50 |
| NVIDIA NIM | — | — |
| Mistral AI Studio | $0.50 | $1.50 |
| Microsoft Foundry | — | — |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 4xH100 |
Capabilities
About Mistral Large 3 675B Instruct
Mistral Large 3 675B Instruct is MistralAI's Mistral Large model. It offers a 128K-token context window and scores 70.2 on τ-bench.
FAQ
What is the context window for Mistral Large 3 675B Instruct on NVIDIA NIM?
Mistral Large 3 675B Instruct supports a 128k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other Mistral Large 3 675B Instruct providers?
Mistral Large 3 675B Instruct is available from 6 providers. The cheapest input pricing is $0.5/1M tokens from OpenRouter.
What API model ID do I use for Mistral Large 3 675B Instruct on NVIDIA NIM?
Use the model ID mistralai/mistral-large-3-675b-instruct-2512 when calling NVIDIA NIM's API.
Who created Mistral Large 3 675B Instruct?
Mistral Large 3 675B Instruct was created by MistralAI as part of the Mistral Large model family.
Is Mistral Large 3 675B Instruct open source?
Mistral Large 3 675B Instruct is open source under Apache 2.0 according to the seed data.