Category

Reasoning models

Reasoning models emit internal chain-of-thought tokens before their final answer. Higher latency, much higher accuracy on hard problems.

9 models in this category. See also the Best AI reasoning models ranking with editorial picks and FAQ.

ModelProviderContextInput price / 1MTier
o1
openai/o1
OpenAI200K
Long context (128K+)
CustomVariable
o3-mini
openai/o3-mini
OpenAI200K
Long context (128K+)
CustomVariable
DeepSeek R1
deepseek/deepseek-r1
DeepSeek128K
Long context (128K+)
CustomVariable
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
Anthropic1M
Ultra context (1M+)
CustomVariable
DeepSeek Chat (legacy id)
deepseek/deepseek-chat
DeepSeek1M
Ultra context (1M+)
CustomVariable
DeepSeek Reasoner (legacy id)
deepseek/deepseek-reasoner
DeepSeek1M
Ultra context (1M+)
CustomVariable
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
DeepSeek1M
Ultra context (1M+)
CustomVariable
Claude Opus 4.7
anthropic/claude-opus-4.7
Anthropic1M
Ultra context (1M+)
CustomVariable
Claude 3 Opus
anthropic/claude-3-opus
Anthropic200K
Long context (128K+)
CustomVariable

Browse other categories