Skip to main content
CodeLint.Dev Dev Tools

LLM Model Comparison

16 models · Updated 2025 · Prices per 1M tokens

16 models
Model Context Input $/1M Output $/1M Released ModalitiesLicenseStrengths
Claude Haiku 4.5
Anthropic · Claude 4
200K$0.80$4.00Jul 2025
textimagecode
Prop.
Fastest ClaudeLow costHigh volume tasks
Claude Opus 4.7
Anthropic · Claude 4
200K$15.00$75.00Jul 2025
textimagecode
Prop.
Complex reasoningLong contextWriting
Claude Sonnet 4.6
Anthropic · Claude 4
200K$3.00$15.00Jul 2025
textimagecode
Prop.
Balanced speed/qualityCodeAnalysis
Command R+
Cohere · Command
128K$2.50$10.00Apr 2024
textcode
Prop.
RAGTool useEnterprise
DeepSeek R1
DeepSeek · DeepSeek
128K$0.55$2.19Jan 2025
textcode
Open
ReasoningMathOpen weights
DeepSeek V3
DeepSeek · DeepSeek
128K$0.27$1.10Dec 2024
textcode
Open
Very low costStrong codingOpen weights
GPT-4o
OpenAI · GPT-4
128K$2.50$10.00May 2024
textimageaudiocode
Prop.
MultimodalReasoningCode
GPT-4o mini
OpenAI · GPT-4
128K$0.15$0.60Jul 2024
textimagecode
Prop.
Low costFastCode
Gemini 2.5 Flash
Google · Gemini 2.5
1M$0.15$0.60May 2025
textimageaudiovideocode
Prop.
Very fast1M contextLow cost
Gemini 2.5 Pro
Google · Gemini 2.5
1M$1.25$10.00Mar 2025
textimageaudiovideocode
Prop.
1M contextMultimodalReasoning
Llama 3.2 Vision 11B
Meta · Llama 3
128KFree / Self-hostFree / Self-hostSep 2024
textimagecode
Open
Open vision modelSelf-hostableLightweight
Llama 3.3 70B
Meta · Llama 3
128KFree / Self-hostFree / Self-hostDec 2024
textcode
Open
Open weightsSelf-hostableStrong reasoning
Mistral 7B
Mistral AI · Mistral
32KFree / Self-hostFree / Self-hostSep 2023
textcode
Open
Fully openEfficientSelf-hostable
Mistral Large 2
Mistral AI · Mistral
128K$2.00$6.00Jul 2024
textcode
Prop.
MultilingualCodeReasoning
o3
OpenAI · o-series
200K$10.00$40.00Apr 2025
textimagecode
Prop.
Deep reasoningMathScience
o4-mini
OpenAI · o-series
200K$1.10$4.40Apr 2025
textimagecode
Prop.
Fast reasoningMathCoding

Prices shown are standard API rates as of May 2025. Batch/cached rates may be lower. Open-source models shown as "Free / Self-host" — inference costs vary by provider.