Mistral Large 2407
Summary
Mistral Large 2407 is an open-weight language model from Mistral AI, released on 24 Jul 2024. It accepts text and generates text, with a 128K-token context window and up to 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $2 per million input tokens and $6 per million output tokens (Snowflake Cortex), across 2 providers we track.
Flagship Mistral model for advanced reasoning, coding, and multilingual work
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Mistral AI |
|---|---|
| Release date | 24 Jul 2024 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mrl [Hugging Face] |
| Parameters | 123B [Hugging Face] |
| Context window | 128K (128,000 tokens) [models.dev] |
| Max output | 8K tokens [models.dev] |
| Knowledge cutoff | 31 Mar 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | No [models.dev] |
| Hugging Face | mistralai/Mistral-Large-Instruct-2407 [Hugging Face] |
Mistral Large 2407 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Snowflake Cortex mistral-large2 | $2 | $6 | – | 128K | models.dev, 18 Nov 2026 |
| OpenRouter mistralai/mistral-large-2407 | $2 | $6 | $0.20 | 131K | OpenRouter, 18 Nov 2026 |
Running Mistral Large 2407 locally
Estimated memory, from the parameter count on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 74 GB | 75 GB | – |
| Q8_0 (8-bit) | 130 GB | 131 GB | – |
| FP16 / BF16 (16-bit) | 245 GB | 246 GB | – |
At 4-bit with an 8K conversation, Mistral Large 2407 needs about 75 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. The model's architecture is not public, so the conversation cache is not included. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Mistral Large 2407?
Mistral Large 2407 has a context window of 128,000 tokens (128K) and can generate up to 8,192 tokens in a single response, according to models.dev.
How much does the Mistral Large 2407 API cost?
Mistral Large 2407 is listed from $2 per million input tokens and $6 per million output tokens (Snowflake Cortex). Prices last verified 18 Nov 2026.
Is Mistral Large 2407 open source?
Mistral Large 2407 is an open-weight model: its weights are published on Hugging Face as mistralai/Mistral-Large-Instruct-2407 under the mrl license. Check the license terms before commercial use.
When was Mistral Large 2407 released?
Mistral AI released Mistral Large 2407 on 24 Jul 2024, according to models.dev.
Which providers offer Mistral Large 2407?
We track Mistral Large 2407 on 2 providers: Snowflake Cortex, OpenRouter.
How much VRAM does Mistral Large 2407 need?
About 75 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 131 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Command R+ | Cohere | 30 Aug 2024 | 128K | $2.50 | $10 | Open |
| Llama 3.1 70B Instruct | Meta | 23 Jul 2024 | 128K | $0.72 | $0.72 | Open |
| Llama 3.1 Euryale 70B v2.2 | Sao10k | 28 Aug 2024 | 131K | $0.85 | $0.85 | Open |
| Aya Expanse 32B | Cohere | 24 Oct 2024 | 128K | $0.50 | $1.50 | Open |
| Magnum v4 72B | Anthracite ORG | 22 Oct 2024 | 33K | $2.50 | $5 | Open |
| Hermes 3 405B Instruct | Nousresearch | 16 Aug 2024 | 131K | – | – | Open |
Change history
- Structured output changed from yes to no
- Max output changed from 105K to 8K
- Context window changed from 131K to 128K
- Tool calling changed from yes to no
- Input modalities changed from text, pdf to text
- Structured output changed from no to yes
- Tool calling changed from no to yes
- Context window changed from 128K to 131K
- Input modalities changed from text to text, pdf
- Max output changed from 8K to 105K
- Context window changed from 131K to 128K
- Max output changed from 105K to 8K
- Tool calling changed from yes to no
- Structured output changed from yes to no
- Input modalities changed from text, pdf to text
- Structured output changed from no to yes
- Context window changed from 128K to 131K
- Max output changed from 8K to 105K
- Input modalities changed from text to text, pdf
- Tool calling changed from no to yes
- Max output changed from 105K to 8K
- Tool calling changed from yes to no
- Context window changed from 131K to 128K
- Structured output changed from yes to no
- Input modalities changed from text, pdf to text