69 Models · 9 Providers

LLM API Pricing Comparison

Compare input & output costs, context windows, and real-world pricing for all major AI models — side by side.

$0.040Cheapest Input/1MMinistral 3B
$150.00Most Expensive/1Mo1-pro
10.0MLargest ContextLlama 4 Scout

API Pricing Index

69 models · Prices per 1 million tokens · Click headers to sort

Model ⇅Input / 1M ↑Output / 1M ⇅Ratio ⇅Context ⇅
Ministral 3BMistral
$0.040
Cheapest		$0.0401.0×
128.0K
GPT-5 NanoOpenAI
$0.050
$0.408.0×
200.0K
Gemini 1.5 FlashGoogle
$0.075
$0.304.0×
1.0M
GPT-4.1 NanoOpenAI
$0.10
$0.404.0×
1.0M
Gemini 2.5 Flash-LiteGoogle
$0.10
$0.404.0×
1.0M
Gemini 2.0 FlashGoogle
$0.10
$0.404.0×
1.0M
Mistral Small 3Mistral
$0.10
$0.303.0×
32.0K
Ministral 8BMistral
$0.10
$0.101.0×
128.0K
Llama 4 ScoutMeta
$0.11
$0.343.1×
10.0M
Max
GPT-4o MiniOpenAI
$0.15
$0.604.0×
128.0K
Mistral NemoMistral
$0.15
$0.151.0×
128.0K
Pixtral 12BMistral
$0.15
$0.151.0×
128.0K
GPT-5.4 NanoOpenAI
$0.20
$1.256.3×
272.0K
Llama 4 MaverickMeta
$0.20
$0.603.0×
1.0M
CodestralMistral
$0.20
$0.603.0×
256.0K
Sonar SmallPerplexity
$0.20
$0.201.0×
127.0K
Grok 4.1 FastxAI
$0.20
$0.502.5×
2.0M
Qwen 2.5 72BQwen
$0.23
$0.401.7×
131.1K
GPT-5 MiniOpenAI
$0.25
$2.008.0×
200.0K
Claude Haiku 3Anthropic
$0.25
$1.255.0×
200.0K
Gemini 3.1 Flash-LiteGoogle
$0.25
$1.506.0×
1.0M
DeepSeek V3DeepSeek
$0.28
$0.421.5×
128.0K
Gemini 2.5 FlashGoogle
$0.30
$2.508.3×
1.0M
GPT-4.1 MiniOpenAI
$0.40
$1.604.0×
1.0M
GPT-3.5 TurboOpenAI
$0.50
$1.503.0×
16.4K
Gemini 3 FlashGoogle
$0.50
$3.006.0×
2.0M
Qwen 3.5 PlusQwen
$0.50
$2.004.0×
1.0M
DeepSeek R1DeepSeek
$0.55
$2.194.0×
128.0K
LLaMA 3.3 70BMeta
$0.59
$0.791.3×
131.1K
GPT-5.4 MiniOpenAI
$0.75
$4.506.0×
272.0K
Claude Haiku 3.5Anthropic
$0.80
$4.005.0×
200.0K
Claude Haiku 4.5Anthropic
$1.00
$5.005.0×
200.0K
Sonar LargePerplexity
$1.00
$1.001.0×
127.0K
o4-miniOpenAI
$1.10
$4.404.0×
200.0K
o3-miniOpenAI
$1.10
$4.404.0×
200.0K
o1-miniOpenAI
$1.10
$4.404.0×
200.0K
GPT-5.1OpenAI
$1.25
$10.008.0×
200.0K
GPT-5OpenAI
$1.25
$10.008.0×
200.0K
Gemini 2.5 ProGoogle
$1.25
$10.008.0×
2.0M
Gemini 1.5 ProGoogle
$1.25
$5.004.0×
2.0M
Grok 4.3xAI
$1.25
$2.502.0×
1.0M
Grok 4.20xAI
$1.25
$2.502.0×
2.0M
GPT-5.2OpenAI
$1.75
$14.008.0×
200.0K
GPT-4.1OpenAI
$2.00
$8.004.0×
1.0M
o3OpenAI
$2.00
$8.004.0×
200.0K
Gemini 3.1 ProGoogle
$2.00
$12.006.0×
2.0M
Mistral Large 3Mistral
$2.00
$6.003.0×
128.0K
Pixtral LargeMistral
$2.00
$6.003.0×
128.0K
GPT-5.4OpenAI
$2.50
$15.006.0×
272.0K
GPT-4oOpenAI
$2.50
$10.004.0×
128.0K
Qwen 3.7 MaxQwen
$2.50
$7.503.0×
1.0M
Claude Sonnet 4.6Anthropic
$3.00
$15.005.0×
1.0M
Claude Sonnet 4.5Anthropic
$3.00
$15.005.0×
200.0K
Claude Sonnet 4Anthropic
$3.00
$15.005.0×
200.0K
Claude Sonnet 3.7Anthropic
$3.00
$15.005.0×
200.0K
Sonar ProPerplexity
$3.00
$15.005.0×
200.0K
Claude Opus 4.7Anthropic
$5.00
$25.005.0×
1.0M
Claude Opus 4.6Anthropic
$5.00
$25.005.0×
1.0M
Claude Opus 4.5Anthropic
$5.00
$25.005.0×
200.0K
Sonar HugePerplexity
$5.00
$5.001.0×
127.0K
GPT-5 ProOpenAI
$15.00
$120.008.0×
200.0K
o1OpenAI
$15.00
$60.004.0×
200.0K
Claude Opus 4.1Anthropic
$15.00
$75.005.0×
200.0K
Claude Opus 4Anthropic
$15.00
$75.005.0×
200.0K
Claude Opus 3Anthropic
$15.00
$75.005.0×
200.0K
o3-proOpenAI
$20.00
$80.004.0×
200.0K
GPT-5.2 ProOpenAI
$21.00
$168.008.0×
200.0K
GPT-5.4 ProOpenAI
$30.00
$180.006.0×
272.0K
o1-proOpenAI
$150.00
$600.004.0×
200.0K
Ministral 3BMistral
Cheapest
Input$0.040/1M tokens
Output$0.040/1M tokens
Ratio1.0×
Context128.0Ktokens
GPT-5 NanoOpenAI
Input$0.050/1M tokens
Output$0.40/1M tokens
Ratio8.0×
Context200.0Ktokens
Gemini 1.5 FlashGoogle
Input$0.075/1M tokens
Output$0.30/1M tokens
Ratio4.0×
Context1.0Mtokens
GPT-4.1 NanoOpenAI
Input$0.10/1M tokens
Output$0.40/1M tokens
Ratio4.0×
Context1.0Mtokens
Gemini 2.5 Flash-LiteGoogle
Input$0.10/1M tokens
Output$0.40/1M tokens
Ratio4.0×
Context1.0Mtokens
Gemini 2.0 FlashGoogle
Input$0.10/1M tokens
Output$0.40/1M tokens
Ratio4.0×
Context1.0Mtokens
Mistral Small 3Mistral
Input$0.10/1M tokens
Output$0.30/1M tokens
Ratio3.0×
Context32.0Ktokens
Ministral 8BMistral
Input$0.10/1M tokens
Output$0.10/1M tokens
Ratio1.0×
Context128.0Ktokens
Llama 4 ScoutMeta
Input$0.11/1M tokens
Output$0.34/1M tokens
Ratio3.1×
Context10.0Mtokens
GPT-4o MiniOpenAI
Input$0.15/1M tokens
Output$0.60/1M tokens
Ratio4.0×
Context128.0Ktokens
Mistral NemoMistral
Input$0.15/1M tokens
Output$0.15/1M tokens
Ratio1.0×
Context128.0Ktokens
Pixtral 12BMistral
Input$0.15/1M tokens
Output$0.15/1M tokens
Ratio1.0×
Context128.0Ktokens
GPT-5.4 NanoOpenAI
Input$0.20/1M tokens
Output$1.25/1M tokens
Ratio6.3×
Context272.0Ktokens
Llama 4 MaverickMeta
Input$0.20/1M tokens
Output$0.60/1M tokens
Ratio3.0×
Context1.0Mtokens
CodestralMistral
Input$0.20/1M tokens
Output$0.60/1M tokens
Ratio3.0×
Context256.0Ktokens
Sonar SmallPerplexity
Input$0.20/1M tokens
Output$0.20/1M tokens
Ratio1.0×
Context127.0Ktokens
Grok 4.1 FastxAI
Input$0.20/1M tokens
Output$0.50/1M tokens
Ratio2.5×
Context2.0Mtokens
Qwen 2.5 72BQwen
Input$0.23/1M tokens
Output$0.40/1M tokens
Ratio1.7×
Context131.1Ktokens
GPT-5 MiniOpenAI
Input$0.25/1M tokens
Output$2.00/1M tokens
Ratio8.0×
Context200.0Ktokens
Claude Haiku 3Anthropic
Input$0.25/1M tokens
Output$1.25/1M tokens
Ratio5.0×
Context200.0Ktokens
Gemini 3.1 Flash-LiteGoogle
Input$0.25/1M tokens
Output$1.50/1M tokens
Ratio6.0×
Context1.0Mtokens
DeepSeek V3DeepSeek
Input$0.28/1M tokens
Output$0.42/1M tokens
Ratio1.5×
Context128.0Ktokens
Gemini 2.5 FlashGoogle
Input$0.30/1M tokens
Output$2.50/1M tokens
Ratio8.3×
Context1.0Mtokens
GPT-4.1 MiniOpenAI
Input$0.40/1M tokens
Output$1.60/1M tokens
Ratio4.0×
Context1.0Mtokens
GPT-3.5 TurboOpenAI
Input$0.50/1M tokens
Output$1.50/1M tokens
Ratio3.0×
Context16.4Ktokens
Gemini 3 FlashGoogle
Input$0.50/1M tokens
Output$3.00/1M tokens
Ratio6.0×
Context2.0Mtokens
Qwen 3.5 PlusQwen
Input$0.50/1M tokens
Output$2.00/1M tokens
Ratio4.0×
Context1.0Mtokens
DeepSeek R1DeepSeek
Input$0.55/1M tokens
Output$2.19/1M tokens
Ratio4.0×
Context128.0Ktokens
LLaMA 3.3 70BMeta
Input$0.59/1M tokens
Output$0.79/1M tokens
Ratio1.3×
Context131.1Ktokens
GPT-5.4 MiniOpenAI
Input$0.75/1M tokens
Output$4.50/1M tokens
Ratio6.0×
Context272.0Ktokens
Claude Haiku 3.5Anthropic
Input$0.80/1M tokens
Output$4.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Claude Haiku 4.5Anthropic
Input$1.00/1M tokens
Output$5.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Sonar LargePerplexity
Input$1.00/1M tokens
Output$1.00/1M tokens
Ratio1.0×
Context127.0Ktokens
o4-miniOpenAI
Input$1.10/1M tokens
Output$4.40/1M tokens
Ratio4.0×
Context200.0Ktokens
o3-miniOpenAI
Input$1.10/1M tokens
Output$4.40/1M tokens
Ratio4.0×
Context200.0Ktokens
o1-miniOpenAI
Input$1.10/1M tokens
Output$4.40/1M tokens
Ratio4.0×
Context200.0Ktokens
GPT-5.1OpenAI
Input$1.25/1M tokens
Output$10.00/1M tokens
Ratio8.0×
Context200.0Ktokens
GPT-5OpenAI
Input$1.25/1M tokens
Output$10.00/1M tokens
Ratio8.0×
Context200.0Ktokens
Gemini 2.5 ProGoogle
Input$1.25/1M tokens
Output$10.00/1M tokens
Ratio8.0×
Context2.0Mtokens
Gemini 1.5 ProGoogle
Input$1.25/1M tokens
Output$5.00/1M tokens
Ratio4.0×
Context2.0Mtokens
Grok 4.3xAI
Input$1.25/1M tokens
Output$2.50/1M tokens
Ratio2.0×
Context1.0Mtokens
Grok 4.20xAI
Input$1.25/1M tokens
Output$2.50/1M tokens
Ratio2.0×
Context2.0Mtokens
GPT-5.2OpenAI
Input$1.75/1M tokens
Output$14.00/1M tokens
Ratio8.0×
Context200.0Ktokens
GPT-4.1OpenAI
Input$2.00/1M tokens
Output$8.00/1M tokens
Ratio4.0×
Context1.0Mtokens
o3OpenAI
Input$2.00/1M tokens
Output$8.00/1M tokens
Ratio4.0×
Context200.0Ktokens
Gemini 3.1 ProGoogle
Input$2.00/1M tokens
Output$12.00/1M tokens
Ratio6.0×
Context2.0Mtokens
Mistral Large 3Mistral
Input$2.00/1M tokens
Output$6.00/1M tokens
Ratio3.0×
Context128.0Ktokens
Pixtral LargeMistral
Input$2.00/1M tokens
Output$6.00/1M tokens
Ratio3.0×
Context128.0Ktokens
GPT-5.4OpenAI
Input$2.50/1M tokens
Output$15.00/1M tokens
Ratio6.0×
Context272.0Ktokens
GPT-4oOpenAI
Input$2.50/1M tokens
Output$10.00/1M tokens
Ratio4.0×
Context128.0Ktokens
Qwen 3.7 MaxQwen
Input$2.50/1M tokens
Output$7.50/1M tokens
Ratio3.0×
Context1.0Mtokens
Claude Sonnet 4.6Anthropic
Input$3.00/1M tokens
Output$15.00/1M tokens
Ratio5.0×
Context1.0Mtokens
Claude Sonnet 4.5Anthropic
Input$3.00/1M tokens
Output$15.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Claude Sonnet 4Anthropic
Input$3.00/1M tokens
Output$15.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Claude Sonnet 3.7Anthropic
Input$3.00/1M tokens
Output$15.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Sonar ProPerplexity
Input$3.00/1M tokens
Output$15.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Claude Opus 4.7Anthropic
Input$5.00/1M tokens
Output$25.00/1M tokens
Ratio5.0×
Context1.0Mtokens
Claude Opus 4.6Anthropic
Input$5.00/1M tokens
Output$25.00/1M tokens
Ratio5.0×
Context1.0Mtokens
Claude Opus 4.5Anthropic
Input$5.00/1M tokens
Output$25.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Sonar HugePerplexity
Input$5.00/1M tokens
Output$5.00/1M tokens
Ratio1.0×
Context127.0Ktokens
GPT-5 ProOpenAI
Input$15.00/1M tokens
Output$120.00/1M tokens
Ratio8.0×
Context200.0Ktokens
o1OpenAI
Input$15.00/1M tokens
Output$60.00/1M tokens
Ratio4.0×
Context200.0Ktokens
Claude Opus 4.1Anthropic
Input$15.00/1M tokens
Output$75.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Claude Opus 4Anthropic
Input$15.00/1M tokens
Output$75.00/1M tokens
Ratio5.0×
Context200.0Ktokens
Claude Opus 3Anthropic
Input$15.00/1M tokens
Output$75.00/1M tokens
Ratio5.0×
Context200.0Ktokens
o3-proOpenAI
Input$20.00/1M tokens
Output$80.00/1M tokens
Ratio4.0×
Context200.0Ktokens
GPT-5.2 ProOpenAI
Input$21.00/1M tokens
Output$168.00/1M tokens
Ratio8.0×
Context200.0Ktokens
GPT-5.4 ProOpenAI
Input$30.00/1M tokens
Output$180.00/1M tokens
Ratio6.0×
Context272.0Ktokens
o1-proOpenAI
Input$150.00/1M tokens
Output$600.00/1M tokens
Ratio4.0×
Context200.0Ktokens
≤ $0.50 input Mid-range ≥ $5.00 input
Try Calculator

Real Cost Comparison by Use Case

See exactly what each model costs for common workloads — from a single chat to filling an entire context window.

💬
Single chat message
~500 tokens
Ministral 3B
$0.00002
GPT-5 Nano
$0.00003
Gemini 1.5 Flash
$0.00004
GPT-4.1 Nano
$0.00005
Gemini 2.5 Flash-Lite
$0.00005
Gemini 2.0 Flash
$0.00005
📝
Blog post summary
~5K tokens
Ministral 3B
$0.00020
GPT-5 Nano
$0.00025
Gemini 1.5 Flash
$0.00038
GPT-4.1 Nano
$0.00050
Gemini 2.5 Flash-Lite
$0.00050
Gemini 2.0 Flash
$0.00050
📄
Document analysis
~50K tokens
Ministral 3B
$0.00200
GPT-5 Nano
$0.00250
Gemini 1.5 Flash
$0.00375
GPT-4.1 Nano
$0.00500
Gemini 2.5 Flash-Lite
$0.00500
Gemini 2.0 Flash
$0.00500
📚
Full context fill
~128K tokens
Ministral 3B
$0.00512
GPT-5 Nano
$0.00640
Gemini 1.5 Flash
$0.00960
GPT-4.1 Nano
$0.0128
Gemini 2.5 Flash-Lite
$0.0128
Gemini 2.0 Flash
$0.0128

Key Pricing Takeaways for 2026

Cheapest Overall

Ministral 3B

At $0.040 per 1M input tokens, Ministral 3B is the most affordable major LLM API. Ideal for high-volume, simple tasks where cost efficiency is paramount.

Best Value Mid-Tier

DeepSeek V3

DeepSeek V3 offers GPT-4-class reasoning at $0.27/$1.10 per 1M tokens — approximately 9× cheaper than GPT-4o. Best choice for developers who need strong performance on a budget.

Largest Context Window

Llama 4 Scout

Llama 4 Scout's 10.0M token context window dwarfs all competitors. For processing entire codebases or very long documents, it's unmatched in capacity.

Best for Quality-Critical

Claude Opus 4.7

Despite premium pricing at $5.00/$25.00 per 1M tokens, Claude Opus 4.7 remains the go-to for tasks where output quality matters most — complex reasoning, nuanced writing, and multi-step analysis.

Ready to calculate your actual costs?

Paste your prompt into our free token calculator and see exact token counts, cost breakdowns, and monthly projections for any model.

Open Token Calculator