Reference
LLM Navigation
Compare specs, pricing, and capabilities of major language models. Find the right model for your use case.
Last updated: December 2024
9
Models Tracked
4
Providers
2M
Max Context
$0.07
Lowest Cost/1M
Model Comparison
| Model | Provider | Context | Input $/1M | Output $/1M | Best For |
|---|---|---|---|---|---|
GPT-4oFRONTIER | OpenAI | 128K | $2.5 | $10.0 | General reasoningCode generation |
GPT-4o-miniFAST | OpenAI | 128K | $0.15 | $0.60 | Simple tasksHigh volume |
Claude 3.5 SonnetFRONTIER | Anthropic | 200K | $3.0 | $15.0 | Code generationLong context |
Claude 3.5 HaikuFAST | Anthropic | 200K | $0.80 | $4.0 | Fast responsesSimple tasks |
Gemini 2.0 FlashFAST | 1.0M | $0.07 | $0.30 | Ultra-long contextMulti-modal | |
Gemini 1.5 ProFRONTIER | 2.0M | $1.3 | $5.0 | 1M+ contextVideo understanding | |
DeepSeek V3 | DeepSeek | 128K | $0.27 | $1.1 | Code generationMath |
o1FRONTIER | OpenAI | 200K | $15.0 | $60.0 | Complex reasoningMath |
o1-mini | OpenAI | 128K | $3.0 | $12.0 | STEM reasoningCode |
Quick Reference
Best for Reasoning
- GPT-4o
- Claude 3.5 Sonnet
- Gemini 1.5 Pro
Best for Speed
- GPT-4o-mini
- Claude 3.5 Haiku
- Gemini 2.0 Flash
Best Value
- Gemini 2.0 Flash — $0.07/M
- GPT-4o-mini — $0.15/M
- DeepSeek V3 — $0.27/M
Want weekly updates and deeper analysis? Get LM Frontier Pro.
Get Pro Access