Mistral Large 2
Mistral's flagship 123B model with strong multilingual and coding performance. Supports 128K context.
128K
tokens
8K
tokens
$2
per 1M tokens
$6
per 1M tokens
78
tokens/sec
Nov 2024
2024-11-18
$4.00
per 1M tokens
19.8
quality per $
Capabilities
Benchmarks
Price vs Quality
Context Window in Context
- Grok 3131K
- ▸ Mistral Large 2128K
- GPT-4o128K
- GPT-4o Mini128K
- DeepSeek V3128K
- DeepSeek R1128K
- Command R+128K
- Gemma 4 27B128K
Pricing History
Mistral Large 2을(를) 여기서 바로 사용해 보세요
Swfte Connect를 통해 Mistral Large 2에 프롬프트를 바로 보냅니다. 계정도 키도 필요 없습니다.
출력 1024 토큰, 시간당 20회로 제한됩니다. 전체 제어는 playground에서 가능합니다.
About Mistral Large 2
Mistral Large 2 is a flagship AI model by Mistral AI, released on November 18, 2024. It supports a context window of 128K tokens and can generate up to 8K output tokens.
At $2 per million input tokens and $6 per million output tokens, its blended cost of $4.00/1M tokens puts it in the mid-range pricing tier. Its value score of 19.8 reflects the balance of quality and cost.
Using Mistral Large 2 with Swfte
Access Mistral Large 2 through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Mistral Large 2 in our AI Playground before integrating.