Skip to main content

Large Language Models (LLMs)

Compare pricing for top language models including GPT-4, Claude, Gemini, Mistral, Llama, and more.

All LLM Providers

VendorModelInput /1MOutput /1MContextFree Tier
OpenAIGPT-4o$2.50$10.00128k100k/mo
OpenAIGPT-4o-mini$0.15$0.60128k100k/mo
OpenAIGPT-4 Turbo$10.00$30.00128k100k/mo
OpenAIo1-preview$15.00$60.00128k100k/mo
OpenAIo1-mini$3.00$12.00128k100k/mo
AnthropicClaude 3.5 Sonnet$3.00$15.00200kLimited
AnthropicClaude 3.5 Haiku$0.25$1.25200kLimited
AnthropicClaude 3 Opus$15.00$75.00200kLimited
GoogleGemini 1.5 Pro$1.25$5.002M1M/mo
GoogleGemini 1.5 Flash$0.075$0.301M1M/mo
GoogleGemini 2.0 Flash$0.10$0.401M1M/mo
MetaLlama 3.1 405B$3.50$3.50128kFree (local)
MetaLlama 3.1 70B$0.65$2.75128kFree (local)
MetaLlama 3.1 8B$0.22$0.22128kFree (local)
MetaLlama 3.2 90B Vision$0.90$3.60127kFree (local)
MistralMistral Large$2.00$6.00128k100k/mo
MistralMistral Nemo$0.15$0.15128k100k/mo
MistralMistral Small$0.60$1.80128k100k/mo
MistralCodestral$0.20$0.7032kFree (beta)
CohereCommand R+$3.00$15.00128k10k/mo
CohereCommand R$0.50$1.50128k10k/mo
CohereCommand$0.30$1.5032k10k/mo
AWS BedrockClaude 3.5 Sonnet$3.00$15.00200kVia AWS
AWS BedrockLlama 3.1 70B$0.65$2.75128kVia AWS
Azure OpenAIGPT-4o$2.50$10.00128k$200 credit
PerplexitySonar Large$3.00$15.00128kAPI pricing
PerplexitySonar Small$0.20$0.70128kAPI pricing
xAIGrok-2$2.00$10.00131k$15/mo
xAIGrok-1.5$5.00$15.00131kAPI pricing

By Price (Input)

Cheapest First:

  1. Google Gemini 1.5 Flash - $0.075/1M
  2. Mistral Nemo - $0.15/1M
  3. GPT-4o-mini - $0.15/1M
  4. Llama 3.1 8B - $0.22/1M
  5. Cohere Command - $0.30/1M

By Context Window

Longest Context:

  1. Google Gemini 1.5 Pro - 2M tokens
  2. Claude 3.5 Sonnet/Opus - 200k tokens
  3. GPT-4o/GPT-4 Turbo - 128k tokens
  4. Llama 3.1 models - 128k tokens

Reasoning Models

ModelInput /1MOutput /1MNotes
OpenAI o1-preview$15.00$60.00Advanced reasoning
OpenAI o1-mini$3.00$12.00Fast reasoning
Claude 3.5 Sonnet$3.00$15.00Strong reasoning
Gemini 1.5 Pro$1.25$5.00Good reasoning

Open Source Models

ModelProviderInput /1MOutput /1MLocal Cost
Llama 3.1 405BMeta$3.50$3.50GPU dependent
Llama 3.1 70BMeta$0.65$2.75GPU dependent
Llama 3.1 8BMeta$0.22$0.22GPU dependent
Mistral LargeMistral$2.00$6.00GPU dependent
Mistral NemoMistral$0.15$0.15GPU dependent
Code Llama 70BMeta$0.65$2.75GPU dependent

Best For

NeedRecommended
Best overallGPT-4o or Claude 3.5 Sonnet
Budget tasksGPT-4o-mini or Gemini Flash
Long documentsGemini 1.5 Pro
Complex reasoningClaude 3.5 Sonnet/Opus
RAG applicationsCommand R+ or Gemini Flash
Open sourceLlama 3.1 70B or Mistral Large
Code generationCodestral or Claude 3.5 Sonnet
ResearchGemini 1.5 Pro or Claude 3.5 Opus