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
GPT OSS 120B	OpenAI	0.039	0.190	compare (17)	131K	131K	24.5#1	15.5#1
Llama 3.3 70B Instruct	Meta	0.100	0.300	compare (16)	131K	120K	14.5#2	10.7#2
Mistral Large	Mistral AI	2.00	6.00	compare (7)	262K	16K	9.9#3	N/A
Llama 3.2 3B Instruct	Meta	0.015	0.020	compare (9)	131K	32K	9.7#4	N/A
Mistral Small	Mistral AI	0.100	0.300	compare (6)	262K	8K	9.0#6	N/A
Mistral Medium	Mistral AI	0.400	2.00	compare (4)	131K	64K	9.0#5	N/A
Granite 3.3 8B	IBM	0.030	0.200	compare (2)	8K	8K	7.0#7	3.4#3
Llama 3.2 1B Instruct	Meta	0.027	0.080	compare (5)	128K	16K	6.3#8	0.6#4
Allam 1 13B Instruct	SDAIA	1.80	1.80	compare (1)	8K	8K	N/A	N/A
Flan-T5 XL 3B	Google	0.600	0.600	compare (1)	8K	8K	N/A	N/A
Granite 2 13B Chat	IBM	0.600	0.600	compare (1)	8K	8K	N/A	N/A
Granite 2 13B Instruct	IBM	0.600	0.600	compare (1)	8K	8K	N/A	N/A
Granite 3 8B Instruct	IBM	0.200	0.200	compare (1)	8K	1K	N/A	N/A
Granite 4 Small	IBM	0.060	0.250	compare (1)	20K	N/A	N/A	N/A
Granite Guardian 3.2 2B	IBM	0.100	0.100	compare (1)	8K	8K	N/A	N/A
Granite Guardian 3.3 8B	IBM	0.200	0.200	compare (1)	8K	8K	N/A	N/A
Granite TTM 2	IBM	0.380	0.380	compare (1)	512	512	N/A	N/A
Granite Vision 3.2 2B	IBM	0.100	0.100	compare (1)	8K	8K	N/A	N/A
Jais 13B Chat	Core42	0.500	2.00	compare (1)	8K	8K	N/A	N/A
Llama 3.2 11B Vision Instruct	Meta	0.015	0.025	compare (7)	131K	16K	N/A	N/A
Llama 3.2 90B Vision Instruct	Meta	0.900	0.900	compare (4)	128K	16K	N/A	N/A
Llama 4 Maverick 17B	Meta	0.350	1.40	compare (1)	128K	N/A	N/A	N/A
Llama Guard 3 11B Vision	Meta	0.350	0.350	compare (1)	128K	N/A	N/A	N/A
Mistral Small 3.1 24B	Mistral AI	0.100	0.300	compare (2)	128K	N/A	N/A	N/A
mT0 XXL 13B	BigScience	0.500	2.00	compare (1)	8K	8K	N/A	N/A
Pixtral 12B	Mistral AI	0.150	0.150	compare (3)	128K	4K	N/A	N/A
Whisper 3 Large Turbo	OpenAI	N/A	N/A	compare (2)	N/A	N/A	N/A	N/A

AI Model Comparison