MAMistral AI/ Mistral
Mistral Large 3
mistral/mistral-large-2512
Mistral Large 3, is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. It features 41B active parameters and 675B total parameters.
Model information
Released
2025-12-02
Context window
256K
Max output
262K
Model parameters
675B
Active parameters
41B
Weights
Open
Modalities
Input
ImageText
Output
Text
Identity
- Version
- 25.12
- Knowledge cutoff
- 2024-11
- License
- Apache-2.0
- Aliases
- Mistral Large 3
Resources
Capabilities
AttachmentsOpen weightStructuredTemperatureTool call
Official price
input $0.5/M · output $1.5/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| LLM Gateway | mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callTemperature | - | input $0.5/M · output $1.5/M | Yes | ||
| 302.AI | mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callTemperature | - | input $1.1/M · output $3.3/M | Yes | ||
| Mistral | mistral-large-2512 | custom | 256K | 262K | AttachmentsTool callTemperature | - | input $0.5/M · output $1.5/M | Yes | ||
| Merge Gateway | mistral/mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callStructuredTemperature | - | input $0.5/M · output $1.5/M cache read $0.05/M | Yes | ||
| Cortecs | mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callTemperature | - | input $0.5/M · output $1.5/M cache read $0.05/M | Yes | ||
| OpenRouter | mistralai/mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callStructuredTemperature | - | input $0.5/M · output $1.5/M cache read $0.05/M | Yes | ||
| AnyAPI | mistralai/mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callTemperature | - | - | Yes | ||
| Kilo Gateway | mistralai/mistral-large-2512 | openai_chat | 256K | 262K | AttachmentsTool callStructuredTemperature | - | input $0.5/M · output $1.5/M cache read $0.05/M | Yes |