GPT-4o mini vs Yi-Large

Performance benchmarks + pricing comparison — updated April 2026

GPT-4o mini

OpenAI

Affordable small model. Fast and cost-effective for high-volume coding tasks.

Input	$0.150/M
Output	$0.600/M
Context	128K tokens
Best For	High-volume tasks, simple coding, cost-sensitive projects
Benchmark	58/100

01.ai

01.ai's flagship model. Strong bilingual capabilities for enterprise applications.

Input	$2.50/M
Output	$10.00/M
Context	32K tokens
Best For	Enterprise Chinese-English applications, analysis

Estimated cost per project with 30% cache hit rate. Actual costs may vary based on usage patterns.

Scenario	GPT-4o mini	Yi-Large	Savings
Small Script (1K lines)	$0.02	$0.39	GPT-4o mini saves $0.36 (94%)
Medium Feature (10K lines)	$0.18	$2.88	GPT-4o mini saves $2.69 (94%)
Large Project (50K lines)	$0.92	$14.38	GPT-4o mini saves $13.46 (94%)
Code Review (5K lines)	$0.05	$0.69	GPT-4o mini saves $0.64 (93%)

GPT-4o mini wins on both price and performance — $0.150/M input with a benchmark score of N/A/100.

For most developers, this is the clear choice between these two models.

Anthropic's balanced model for coding and general tasks. Best price-performance ratio in the Claude family.

Anthropic's most powerful model. Best for complex reasoning and challenging coding tasks.

Previous generation Sonnet. Still excellent for coding tasks at the same price point.

Fast, cost-effective model for high-volume tasks. Great for code review and simple queries.

First generation Opus. Highest reasoning capability in the Claude 3 family.

First generation Sonnet. Balanced performance for general tasks.