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
Claude Opus 4.5	Anthropic	5.00	25.00	compare (9)	410K	64K	43.1#1	42.9#1
Claude Sonnet 4.5	Anthropic	3.00	15.00	compare (10)	1.0M	64K	37.1#2	33.5#4
Claude Opus 4.1	Anthropic	15.00	75.00	compare (7)	200K	32K	36.0#3	36.5#2
Claude Sonnet 4	Anthropic	3.00	15.00	compare (10)	1.0M	64K	33.0#5	30.6#6
Claude Opus 4	Anthropic	15.00	75.00	compare (9)	410K	32K	33.0#4	34.0#3
Claude Haiku 4.5	Anthropic	1.00	5.00	compare (9)	200K	64K	31.1#6	29.6#7
Claude Sonnet 3.7	Anthropic	3.00	15.00	compare (10)	200K	128K	30.8#7	26.7#9
Gemini 2.5 Pro	Google	1.25	10.00	compare (8)	1.0M	66K	29.5#8	31.9#5
GPT-5.1	OpenAI	1.25	10.00	compare (7)	410K	128K	27.4#9	27.3#8
GPT OSS 120B	OpenAI	0.039	0.190	compare (17)	131K	131K	24.5#10	15.5#14
GPT-5	OpenAI	1.25	10.00	compare (9)	410K	128K	21.8#11	21.2#11
GPT OSS 20B	OpenAI	0.030	0.140	compare (13)	131K	131K	20.8#12	14.4#16
GPT-5 Mini	OpenAI	0.250	2.00	compare (8)	400K	128K	20.7#13	21.9#10
Llama 4 Maverick	Meta	0.150	0.600	compare (4)	1.0M	16K	18.4#14	15.6#13
Gemini 2.5 Flash	Google	0.150	0.600	compare (9)	1.0M	66K	17.8#15	17.8#12
Llama 3.1 405B Instruct	Meta	0.120	0.300	compare (11)	131K	16K	17.4#16	14.5#15
Llama 3.3 70B Instruct	Meta	0.100	0.300	compare (16)	131K	120K	14.5#17	10.7#18
GPT-5 Nano	OpenAI	0.050	0.400	compare (7)	400K	128K	13.8#18	14.2#17
Llama 3.1 8B Instruct	Meta	0.020	0.040	compare (15)	200K	128K	11.8#19	4.9#21
Llama 3 70B Instruct	Meta	0.120	0.300	compare (7)	131K	8K	8.9#20	6.8#19
Gemma 3 12B Instruct	Google	0.150	0.500	compare (1)	128K	32K	8.8#21	6.3#20
Llama 2 70B Chat	Meta	0.500	0.900	compare (6)	4K	4K	8.4#22	N/A
Mixtral 8x7B Instruct	Mistral AI	0.070	0.280	compare (9)	33K	16K	7.7#23	N/A
BGE Large EN	Baai	0.100	N/A	compare (1)	512	N/A	N/A	N/A
Claude Sonnet 4.1	Anthropic	3.00	15.00	compare (1)	200K	64K	N/A	N/A
GTE Large EN	Alibaba	0.130	N/A	compare (1)	8K	N/A	N/A	N/A
MPT 30B Instruct	Mosaicml	1.00	1.00	compare (1)	8K	8K	N/A	N/A
MPT 7B Instruct	Mosaicml	0.500	N/A	compare (1)	8K	8K	N/A	N/A

AI Model Comparison