LLM Reference

Kimi K2.5 vs Mistral Large 3 675B Instruct

Kimi K2.5 (2026) and Mistral Large 3 675B Instruct (2025) compare a coding-specialized model against a standalone API model. Kimi K2.5 ships a 256k-token context window, while Mistral Large 3 675B Instruct ships a 128k-token context window. On MMLU PRO, Kimi K2.5 leads by 1.6 pts. On pricing, Kimi K2.5 costs $0.44/1M input tokens versus $0.50/1M for the alternative. This page treats the result as workflow and deployment fit, not a universal model winner.

Treat this as a product-type comparison: Kimi K2.5 is coding-specialized model, while Mistral Large 3 675B Instruct is standalone API model. Choose based on workflow fit before reading any benchmark or price row as decisive.

Decision scorecard

Local evidence first
SignalKimi K2.5Mistral Large 3 675B Instruct
Product typeCoding-specialized modelStandalone API model
Best forcustom coding agents, code generation, and tool loopsmultimodal apps and provider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window256k128k
Cheapest output$2/1M tokens$1.50/1M tokens
Provider routes10 tracked6 tracked
Shared benchmarksMMLU PRO leader4 shared

Decision tradeoffs

Choose Kimi K2.5 when...
  • Kimi K2.5 holds a shared-benchmark lead on MMLU PRO, ahead by 1.6 points.
  • Kimi K2.5 has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Kimi K2.5 has broader tracked provider coverage for fallback and route flexibility.
  • Kimi K2.5 uniquely exposes JSON / Tool use in local model data.
  • Local decision data tags Kimi K2.5 for Coding, RAG, and Agents.
Choose Mistral Large 3 675B Instruct when...
  • Mistral Large 3 675B Instruct has the lower cheapest tracked output price at $1.50/1M tokens.
  • Local decision data tags Mistral Large 3 675B Instruct for Coding, RAG, and Agents.

Monthly cost at traffic

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

Lower estimate Mistral Large 3 675B Instruct

Kimi K2.5

$852

Cheapest tracked route/tier: OpenRouter

Mistral Large 3 675B Instruct

$775

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $77.00. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Kimi K2.5 -> Mistral Large 3 675B Instruct
  • Provider overlap exists on OpenRouter, AWS Bedrock, and NVIDIA NIM; start route-level A/B tests there.
  • Mistral Large 3 675B Instruct is $0.50/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for JSON / Tool use before moving production traffic.
Mistral Large 3 675B Instruct -> Kimi K2.5
  • Provider overlap exists on OpenRouter, NVIDIA NIM, and AWS Bedrock; start route-level A/B tests there.
  • Kimi K2.5 is $0.50/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Kimi K2.5 adds JSON / Tool use in local capability data.

Specs

Specification
Released2026-03-152025-12-01
Context window256k128k
Parameters1T (MoE, 384 experts)675B
ArchitectureMixture of ExpertsDecoder Only
LicenseProprietaryApache 2.0OSI-approved
OpennessProprietaryOpen source
WeightsNot releasedUnknown
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: permitted
Knowledge cutoff-2024-11

Pricing and availability

Pricing attributeKimi K2.5Mistral Large 3 675B Instruct
Input price$0.44/1M tokens$0.50/1M tokens
Output price$2/1M tokens$1.50/1M tokens
Providers

Capabilities

CapabilityKimi K2.5Mistral Large 3 675B Instruct
VisionYesYes
MultimodalYesYes
ReasoningNoNo
JSON / Tool useYesNo
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkKimi K2.5Mistral Large 3 675B Instruct
MMLU PRO87.185.5
Google-Proof Q&A87.943.9
LiveCodeBench85.082.8
τ-bench74.270.2

Continue comparing

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