OpenAI
Find the right AI model for your workload
Start with capabilities, pricing, context and model families—not a leaderboard alone.
Explore models by your constraints
Pricing stays connected to the existing llmprice.app data pipeline.
OpenAI
gpt-5.6-terra
OpenAI
gpt-5.6-luna
OpenAI
gpt-5.5
OpenAI
gpt-5.4
OpenAI
gpt-5.4-mini
OpenAI
gpt-5.4-nano
OpenAI
gpt-4o
OpenAI
gpt-4o-mini
OpenAI
o3
OpenAI
o4-mini
Anthropic
claude-fable-5
Anthropic
claude-mythos-5
Anthropic
claude-opus-4-8
Anthropic
claude-opus-4-6
Anthropic
claude-sonnet-5
Anthropic
claude-sonnet-4-6
Anthropic
claude-haiku-4-5
gemini-3.1-flash-lite
gemini-3.5-flash
gemini-3.1-pro
gemini-2.5-pro
gemini-2.5-flash
Mistral
mistral-large-3
Mistral
mistral-medium-3.5
Mistral
codestral-latest
DeepSeek
deepseek-chat-v4
DeepSeek
deepseek-reasoner-v4
xAI
grok-4.3
Together AI
meta-llama/Llama-3.3-70B-Instruct-Turbo
Together AI
Qwen/Qwen2.5-72B-Instruct-Turbo
Cohere
command-a
Cohere
command-r
Groq
llama-3.3-70b-versatile
Microsoft
Phi-4
Microsoft
Phi-4-mini
Microsoft
MAI-DS-R1
Microsoft
Llama-3.3-70B-Instruct
Microsoft
Mistral-Large
Zhipu
GLM-5.2
Choose by scenario, not leaderboard position
Start with coding, RAG or high-throughput needs, then validate price and specs.
New to model selection? Start here
01How should I compare API models?+
Define the quality bar first, then compare price, latency, context and modalities.
02Is a larger context window always better?+
No. More context can increase cost and latency; retrieval and caching also matter.
03How do I estimate monthly LLM cost?+
Multiply tokens per request by monthly volume, then apply input and output rates.