LLM Reference

Mistral Large 2 vs Qwen2.5-72B-Instruct

Mistral Large 2 (2025) and Qwen2.5-72B-Instruct (2024) are compact production models from MistralAI and Alibaba. Mistral Large 2 ships a 128k-token context window, while Qwen2.5-72B-Instruct ships a 128k-token context window. On HumanEval, Qwen2.5-72B-Instruct leads by 1.8 pts. On pricing, Qwen2.5-72B-Instruct costs $0.18/1M input tokens versus $0.48/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Qwen2.5-72B-Instruct is ~167% cheaper at $0.18/1M; pay for Mistral Large 2 only for vision-heavy evaluation.

Decision scorecard

Local evidence first
SignalMistral Large 2Qwen2.5-72B-Instruct
Best formultimodal apps, tool-calling agents, and provider-routed productionprovider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Long context
Context window128k128k
Cheapest output$2.40/1M tokens$0.54/1M tokens
Provider routes3 tracked7 tracked
Shared benchmarks4 sharedHumanEval leader

Decision tradeoffs

Choose Mistral Large 2 when...
  • Mistral Large 2 uniquely exposes Vision, Multimodal, and JSON / Tool use in local model data.
  • Local decision data tags Mistral Large 2 for Coding, RAG, and Agents.
Choose Qwen2.5-72B-Instruct when...
  • Qwen2.5-72B-Instruct holds a shared-benchmark lead on HumanEval, ahead by 1.8 points.
  • Qwen2.5-72B-Instruct has the lower cheapest tracked output price at $0.54/1M tokens.
  • Qwen2.5-72B-Instruct has broader tracked provider coverage for fallback and route flexibility.
  • Local decision data tags Qwen2.5-72B-Instruct for Coding, RAG, and Long context.

Monthly cost at traffic

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

Lower estimate Qwen2.5-72B-Instruct

Mistral Large 2

$984

Cheapest tracked route/tier: AWS Bedrock

Qwen2.5-72B-Instruct

$279

Cheapest tracked route/tier: Chutes AI

Estimated monthly gap: $705. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Mistral Large 2 -> Qwen2.5-72B-Instruct
  • No overlapping tracked provider route is sourced for Mistral Large 2 and Qwen2.5-72B-Instruct; plan for SDK, billing, or endpoint changes.
  • Qwen2.5-72B-Instruct is $1.86/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Vision, Multimodal, and JSON / Tool use before moving production traffic.
Qwen2.5-72B-Instruct -> Mistral Large 2
  • No overlapping tracked provider route is sourced for Qwen2.5-72B-Instruct and Mistral Large 2; plan for SDK, billing, or endpoint changes.
  • Mistral Large 2 is $1.86/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Mistral Large 2 adds Vision, Multimodal, and JSON / Tool use in local capability data.

Specs

Specification
Released2025-11-252024-06-07
Context window128k128k
Parameters123B72.7B
ArchitectureDecoder OnlyDecoder Only
LicenseMistral LicenseApache 2.0OSI-approved
OpennessOpen weightsOpen source
WeightsUnknownAvailable
CodeUnknownUnknown
Commercial useCommercial use: non-commercialCommercial use: permitted
Knowledge cutoff2025-07-

Pricing and availability

Pricing attributeMistral Large 2Qwen2.5-72B-Instruct
Input price$0.48/1M tokens$0.18/1M tokens
Output price$2.40/1M tokens$0.54/1M tokens
Providers

Capabilities

CapabilityMistral Large 2Qwen2.5-72B-Instruct
VisionYesNo
MultimodalYesNo
ReasoningNoNo
JSON / Tool useYesNo
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkMistral Large 2Qwen2.5-72B-Instruct
HumanEval84.886.6
Chatbot Arena1265.01270.0
Massive Multitask Language Understanding84.088.2
HellaSwag93.895.6

Continue comparing

Last reviewed: 2026-06-30. Data sourced from public model cards and provider documentation.