LLM Reference

Mistral Large 3 675B Instruct vs Phi-4 Mini Flash Reasoning

Mistral Large 3 675B Instruct (2025) and Phi-4 Mini Flash Reasoning (2025) are frontier reasoning models from MistralAI and Microsoft Research. Mistral Large 3 675B Instruct ships a 128k-token context window, while Phi-4 Mini Flash Reasoning ships a 128k-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Mistral Large 3 675B Instruct is safer overall; choose Phi-4 Mini Flash Reasoning when reasoning depth matters.

Decision scorecard

Local evidence first
SignalMistral Large 3 675B InstructPhi-4 Mini Flash Reasoning
Best formultimodal apps and provider-routed productionreasoning-heavy apps
Decision fitCoding, RAG, and AgentsLong context
Context window128k128k
Cheapest output$1.50/1M tokens-
Provider routes6 tracked1 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose Mistral Large 3 675B Instruct when...
  • Mistral Large 3 675B Instruct has broader tracked provider coverage for fallback and route flexibility.
  • Mistral Large 3 675B Instruct uniquely exposes Vision, Multimodal, and Structured outputs in local model data.
  • Local decision data tags Mistral Large 3 675B Instruct for Coding, RAG, and Agents.
Choose Phi-4 Mini Flash Reasoning when...
  • Phi-4 Mini Flash Reasoning uniquely exposes Reasoning in local model data.
  • Local decision data tags Phi-4 Mini Flash Reasoning for Long context.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Mistral Large 3 675B Instruct

$775

Cheapest tracked route/tier: OpenRouter

Phi-4 Mini Flash Reasoning

Unavailable

No complete token price in local provider data

Cost delta unavailable until both models have sourced input and output token prices.

Switch friction

Mistral Large 3 675B Instruct -> Phi-4 Mini Flash Reasoning
  • Provider overlap exists on NVIDIA NIM; start route-level A/B tests there.
  • Check replacement coverage for Vision, Multimodal, and Structured outputs before moving production traffic.
  • Phi-4 Mini Flash Reasoning adds Reasoning in local capability data.
Phi-4 Mini Flash Reasoning -> Mistral Large 3 675B Instruct
  • Provider overlap exists on NVIDIA NIM; start route-level A/B tests there.
  • Check replacement coverage for Reasoning before moving production traffic.
  • Mistral Large 3 675B Instruct adds Vision, Multimodal, and Structured outputs in local capability data.

Specs

Specification
Released2025-12-012025-12-01
Context window128k128k
Parameters675B3.8B
ArchitectureDecoder OnlyDecoder Only
LicenseApache 2.0OSI-approvedMITOSI-approved
OpennessOpen sourceOpen source
WeightsUnknownUnknown
CodeUnknownUnknown
Commercial useCommercial use: permittedCommercial use: permitted
Knowledge cutoff2024-112025-02

Pricing and availability

Pricing attributeMistral Large 3 675B InstructPhi-4 Mini Flash Reasoning
Input price$0.50/1M tokens-
Output price$1.50/1M tokens-
Providers

Capabilities

CapabilityMistral Large 3 675B InstructPhi-4 Mini Flash Reasoning
VisionYesNo
MultimodalYesNo
ReasoningNoYes
JSON / Tool useNoNo
Structured outputsYesNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Continue comparing

Last reviewed: 2026-06-29. Data sourced from public model cards and provider documentation.