Question 1

What is the cheapest AI model for chat?

Accepted Answer

The cheapest AI chat models are typically smaller models like GPT-3.5-turbo, Claude Instant, or open-source models on platforms like Together AI and Groq. Prices can be as low as $0.10-0.25 per million tokens. However, cheaper models may have reduced capabilities compared to flagship models like GPT-4 or Claude 3 Opus. Use CloudPrice to compare current prices across all providers.

Question 2

How much does GPT-4 cost?

Accepted Answer

GPT-4 pricing varies by version. GPT-4 Turbo costs approximately $10 per million input tokens and $30 per million output tokens. GPT-4o is more affordable at around $5/$15 per million tokens. OpenAI also offers GPT-4o-mini at significantly lower prices. Pricing may change, so check CloudPrice for current rates.

Question 3

What is the difference between input and output tokens?

Accepted Answer

Input tokens are the text you send to the AI model (your prompts, context, and conversation history). Output tokens are what the model generates in response. Most AI providers charge differently for input and output tokens, with output tokens typically being 2-4x more expensive because they require more computation to generate.

Question 4

Which AI model has the largest context window?

Accepted Answer

Google's Gemini 1.5 Pro currently offers one of the largest context windows at 1 million tokens. Anthropic's Claude 3 models support 200K tokens, while OpenAI's GPT-4 Turbo supports 128K tokens. Larger context windows allow processing more text in a single request but may cost more.

Question 5

What does 'supports vision' mean for AI models?

Accepted Answer

AI models with vision support can process and understand images in addition to text. You can send images as part of your prompt and the model can describe, analyze, or answer questions about them. Examples include GPT-4 Vision, Claude 3, and Gemini Pro Vision. Vision capabilities typically cost extra per image processed.

Model	Creator	Input Price, $	Output Price, $	Inference Providers	Context	Max Output	Intelligence	Coding
Command R+ 4	Cohere	3.00	15.00	compare (1)	128K	4K	8.3#1	N/A
Command R 3	Cohere	0.500	1.50	compare (1)	128K	4K	7.4#2	N/A
Aya Expanse	Cohere	0.500	1.50	compare (1)	128K	4K	N/A	N/A
Aya Expanse	Cohere	0.500	1.50	compare (1)	8K	4K	N/A	N/A
Command	Cohere	1.00	1.56	compare (2)	128K	4K	N/A	N/A
Command A	Cohere	2.50	10.00	compare (1)	256K	8K	N/A	N/A
Command Light	Cohere	0.300	0.600	compare (1)	4K	4K	N/A	N/A
Command Nightly	Cohere	1.00	2.00	compare (1)	4K	4K	N/A	N/A
Command R	Cohere	0.150	0.600	compare (3)	128K	4K	N/A	N/A
Command R 8	Cohere	0.150	0.150	compare (3)	128K	4K	N/A	N/A
Command R+	Cohere	2.50	10.00	compare (4)	128K	4K	N/A	N/A
Command R+ 8	Cohere	1.56	1.56	compare (3)	128K	4K	N/A	N/A
Command R7B (12-2024)	Cohere	0.037	0.150	compare (2)	128K	4K	N/A	N/A
Embed 2 English	Cohere	0.100	N/A	compare (1)	4K	N/A	N/A	N/A
Embed 2 English Light	Cohere	0.100	N/A	compare (1)	1K	N/A	N/A	N/A
Embed 2 Multilingual	Cohere	0.100	N/A	compare (1)	768	N/A	N/A	N/A
Embed 3 English	Cohere	0.100	N/A	compare (3)	1K	N/A	N/A	N/A
Embed 3 English Light	Cohere	0.100	N/A	compare (2)	1K	N/A	N/A	N/A
Embed 3 Multilingual	Cohere	0.100	N/A	compare (3)	1K	N/A	N/A	N/A
Embed 3 Multilingual Light	Cohere	0.100	N/A	compare (2)	1K	N/A	N/A	N/A
Embed 4	Cohere	0.120	0.470	compare (4)	128K	N/A	N/A	N/A
Rerank 3 English	Cohere	N/A	N/A	compare (2)	4K	4K	N/A	N/A
Rerank 3 Multilingual	Cohere	N/A	N/A	compare (2)	4K	4K	N/A	N/A
Rerank 3.5	Cohere	N/A	N/A	compare (3)	32K	32K	N/A	N/A
Rerank 4 Fast	Cohere	2.00	N/A	compare (2)	33K	N/A	N/A	N/A
Rerank 4 Pro	Cohere	2.50	N/A	compare (2)	33K	N/A	N/A	N/A
Voyage Rerank 2 English	Voyage	N/A	N/A	compare (1)	4K	4K	N/A	N/A
Voyage Rerank 2 Multilingual	Voyage	N/A	N/A	compare (1)	4K	4K	N/A	N/A

AI Model Comparison