Compare the listed model data for LITHOVEX 2.6 Plus by LITHOVEX and LITHOVEX 2.5 Core by LITHOVEX. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
LITHOVEX 2.6 Plus: 200K tokens; LITHOVEX 2.5 Core: 200K tokens. The listed context-window values are equal. LITHOVEX 2.6 Plus is listed for coding, reasoning, agentic workflows, long-context tasks; LITHOVEX 2.5 Core is listed for coding, reasoning, agentic workflows, long-context tasks. Shared catalog benchmark entries: HumanEval: LITHOVEX 2.6 Plus 91.8%; LITHOVEX 2.5 Core 88.4%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Use these model and provider links to verify current specifications, pricing, and availability.
A cost example for 1M input plus 1M output tokens cannot be calculated reliably because separate numeric input and output rates are not listed for both models.
Choose LITHOVEX 2.6 Plus when your task aligns with catalog-listed uses or strengths such as Complex enterprise-grade analysis requiring maximum accuracy and reasoning depth, Long-document processing: legal contracts, technical specifications, research papers, Advanced software engineering: multi-file codebase analysis, architecture design, Creative writing requiring deep narrative reasoning and stylistic control.
Choose LITHOVEX 2.5 Core when your task aligns with catalog-listed uses or strengths such as Full-stack code generation in Python, TypeScript, JavaScript, and modern frameworks, Code debugging, refactoring, and technical debt reduction, SQL query optimization and database schema design, API integration, REST/GraphQL endpoint generation.
LITHOVEX flagship — the smartest, most capable model in the lineup. Effortlessly handles code, deep reasoning, writing, math, research, planning, and everyday questions.
Parameters: 200B+ MoE
Context: 200K tokens
Catalog pricing: Free on LITHOVEX AI
LITHOVEX engineering powerhouse — surgical code specialist tuned for code generation, debugging, refactors, and software architecture.
Parameters: 70B
Context: 200K tokens
Catalog pricing: Free on LITHOVEX AI
| Specification | LITHOVEX 2.6 Plus | LITHOVEX 2.5 Core |
|---|---|---|
| Provider | LITHOVEX | LITHOVEX |
| Parameters | 200B+ MoE | 70B |
| Context window | 200K tokens | 200K tokens |
| Maximum output | Not listed | Not listed |
| Catalog pricing | Free on LITHOVEX AI | Free on LITHOVEX AI |
| Listed input/output cost per 1M tokens | Separate numeric input/output rates not listed | Separate numeric input/output rates not listed |
| License | Proprietary | Proprietary |
| Coding support | Listed | Listed |
| Reasoning support | Listed | Listed |
| Vision input | Not listed | Not listed |
| Multimodal | Not listed | Not listed |
| Open weights | No | No |
| Benchmark: HumanEval | 91.8% | 88.4% |
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Read the LITHOVEX 2.6 Plus model profile and LITHOVEX 2.5 Core model profile, or browse the model directory.