sourc.dev
Home LLMs Tools SaaS APIs
Claude 3.5 Sonnet input $3.00/1M ↓ -50%
GPT-4o input $2.50/1M
Gemini 1.5 Pro input $1.25/1M
Mistral Large input $2.00/1M ↓ -33%
DeepSeek V3 input $0.27/1M
synced 2026-04-05
Claude 3.5 Sonnet input $3.00/1M ↓ -50%
GPT-4o input $2.50/1M
Gemini 1.5 Pro input $1.25/1M
Mistral Large input $2.00/1M ↓ -33%
DeepSeek V3 input $0.27/1M
synced 2026-04-05

Most Context Per Dollar

Models ranked by context window size relative to input token cost. Higher ratios mean more processing capacity for less money.

Methodology: Computed as context_window_tokens / input_price_per_1m. Only models with both values included. Higher is better.

# Model Metric
1 Gemini 1.5 Flash 13,333,333 tokens/$1
2 Gemini 2.0 Flash 10,000,000 tokens/$1
3 Gemini 1.5 Pro 1,600,000 tokens/$1
4 Llama 3.3 70B 1,280,000 tokens/$1
5 Qwen 2.5 72B 1,066,667 tokens/$1
6 GPT-4o mini 853,333 tokens/$1
7 Claude 3 Haiku 800,000 tokens/$1
8 Kimi K2.5 500,000 tokens/$1
9 DeepSeek V3.2 492,308 tokens/$1
10 DeepSeek V3 474,074 tokens/$1
11 Claude 3.5 Haiku 250,000 tokens/$1
12 ERNIE 4.0 152,381 tokens/$1
13 Mistral 7B 131,072 tokens/$1
14 DeepSeek R1 91,429 tokens/$1
15 Claude 3 Sonnet 66,667 tokens/$1
16 Claude Sonnet 4.6 66,667 tokens/$1
17 Claude 3.5 Sonnet 66,667 tokens/$1
18 Gemini 1.0 Pro 65,536 tokens/$1
19 Grok 2 65,536 tokens/$1
20 Mistral Large 2 64,000 tokens/$1
21 Mixtral 8x7B 60,681 tokens/$1
22 GPT-4o 51,200 tokens/$1
23 Command R+ 51,200 tokens/$1
24 Llama 3.1 405B 25,600 tokens/$1
25 Llama 3 70B 16,063 tokens/$1
26 Claude 3 Opus 13,333 tokens/$1
27 o1 13,333 tokens/$1
28 GPT-4 Turbo 12,800 tokens/$1
29 Claude 2 12,500 tokens/$1
30 GPT-3.5 Turbo 10,923 tokens/$1
31 Llama 2 70B 4,551 tokens/$1
32 GPT-4 273 tokens/$1
33 GPT-3 (davinci-002) 68 tokens/$1
← All leaderboards