TokenCosts AI.iov1.0
Back to Models Directory
Mistralmistral-large-2512

Mistral: Mistral Large 3 2512 API Pricing

Official PricingCall via OpenRouter

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Base Input Price$0.50/ 1M tokens
Base Output Price$1.50/ 1M tokens
Prompt Cache Read$0.050-90% discount
Batch API Rate-50%24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
Mistral Direct$0.50$1.50SupportedConnect
OpenRouter$0.50$1.50SupportedConnect

Head-to-Head Comparisons for Mistral: Mistral Large 3 2512

Mistral: Mistral Large 3 2512 vs OpenAI: GPT-6.1 Sol$0.5/M vs $2/M
Mistral: Mistral Large 3 2512 vs GPT-4o (Omni)$0.5/M vs $2.5/M
Mistral: Mistral Large 3 2512 vs Claude 3.5 Sonnet$0.5/M vs $3/M
Mistral: Mistral Large 3 2512 vs DeepSeek-V3 (deepseek-chat)$0.5/M vs $0.27/M