LLM Pricing
Compare and calculate the latest prices for LLM (Large Language Models) APIs from leading providers such as OpenAI GPT-4, Anthropic Claude, Google Gemini, Mate Llama 3, and more. Use our streamlined LLM Price Check tool to start optimizing your AI budget efficiently today!
| Model | Provider | Context | Input $/1M | Output $/1M | Per Call | Total | Free trial |
|---|---|---|---|---|---|---|---|
| gpt-4o | 
OpenAI
| 128K | $5 | $15 | $0.016 | $1.6 | Chat |
| gpt-4o-2024-08-06 |
OpenAI
| 128K | $2.5 | $10 | $0.0105 | $1.05 | Chat |
| gpt-4o-mini |
OpenAI
| 128K | $0.15 | $0.6 | $0.0006 | $0.06 | Chat |
| gpt-4o-2024-05-13 |
OpenAI
| 128K | $5 | $15 | $0.016 | $1.6 | Chat |
| gpt-4-turbo-2024-04-09 |
OpenAI
| 128K | $10 | $30 | $0.032 | $3.2 | Chat |
| gpt-4 |
OpenAI
| 8K | $30 | $60 | $0.066 | $6.6 | Chat |
| gpt-4-32k |
OpenAI
| 32K | $60 | $120 | $0.132 | $13.2 | Chat |
| gpt-3.5-turbo-0125 |
OpenAI
| 16K | $0.5 | $1.5 | $0.0016 | $0.16 | Chat |
| gpt-3.5-turbo-instruct |
OpenAI
| 4K | $1.5 | $2 | $0.0023 | $0.23 | Chat |
| claude-3-opus | 
Anthropic
| 200K | $15 | $75 | $0.078 | $7.8 | Chat |
| claude-3-sonnet |
Anthropic
| 200K | $3 | $15 | $0.0156 | $1.56 | Chat |
| claude-3-haiku |
Anthropic
| 200K | $0.25 | $1.25 | $0.0013 | $0.13 | Chat |
| claude-2.1 |
Anthropic
| 200K | $8 | $24 | $0.0256 | $2.56 | Chat |
| claude-2.0 |
Anthropic
| 100K | $8 | $24 | $0.0256 | $2.56 | Chat |
| claude-instant-1.2 |
Anthropic
| 100K | $0.8 | $2.4 | $0.0026 | $0.26 | Chat |
| llama-3.1-405b-instruct | 
Fireworks
| 128K | $3 | $3 | $0.0036 | $0.36 | Chat |
| llama-3.1-70b-instruct | 
Deepinfra
| 128K | $0.52 | $0.75 | $0.0009 | $0.09 | Chat |
| llama-3.1-8b-instruct |
Deepinfra
| 128K | $0.09 | $0.09 | $0.0001 | $0.01 | Chat |
| llama-3-70b-instruct |
Deepinfra
| 8K | $0.59 | $0.79 | $0.0009 | $0.09 | Chat |
| llama-3-8b-instruct |
Deepinfra
| 8K | $0.08 | $0.08 | $0.0001 | $0.01 | Chat |
| gemini-pro | 
Google
| 32K | $0.5 | $1.5 | $0.0016 | $0.16 | Chat |
| gemini-1.5-pro |
Google
| 1M | $3.5 | $10.5 | $0.0112 | $1.12 | Chat |
| gemini-flash-1.5 |
Google
| 2.8M | $0.075 | $0.3 | $0.0003 | $0.03 | Chat |
| gemma-7b-it |
Deepinfra
| 8K | $0.07 | $0.07 | $0.0001 | $0.01 | Chat |
| mistral-large | 
Mistral
| 32K | $8 | $24 | $0.0256 | $2.56 | Chat |
| mistral-medium |
Mistral
| 32K | $2.7 | $8.1 | $0.0086 | $0.86 | Chat |
| mistral-small |
Mistral
| 32K | $2 | $6 | $0.0064 | $0.64 | Chat |
| mixtral-8x7b |
Mistral
| 32K | $0.7 | $0.7 | $0.0008 | $0.08 | Chat |
| mistral-7b |
Mistral
| 32K | $0.25 | $0.25 | $0.0003 | $0.03 | Chat |
| command-r-plus | 
Cohere
| 128K | $3 | $15 | $0.0156 | $1.56 | Chat |
| command-r |
Cohere
| 4K | $0.5 | $1.5 | $0.0016 | $0.16 | Chat |
| command |
Cohere
| 4K | $0.3 | $0.6 | $0.0007 | $0.07 | Chat |
| pplx-70b-online | 
Perplexity
| 4K | $1 | $1 | $0.0012 | $0.12 | Chat |
| pplx-7b-online |
Perplexity
| 4K | $0.2 | $0.2 | $0.0002 | $0.02 | Chat |
| openchat-7b | 
OpenChat
| 8K | $0.13 | $0.13 | $0.0002 | $0.02 | Chat |
| deepseek-v2 | 
DeepSeek
| 32K | $0.14 | $0.28 | $0.0003 | $0.03 | Chat |
| llama-3-70b | 
Groq
| 8K | $0.59 | $0.79 | $0.0009 | $0.09 | Chat |
| llama-3-8b |
Groq
| 8K | $0.05 | $0.1 | $0.0001 | $0.01 | Chat |
| llama-2-70b |
Groq
| 4K | $0.64 | $0.8 | $0.0009 | $0.09 | Chat |
| llama-2-7b |
Groq
| 2K | $0.1 | $0.1 | $0.0001 | $0.01 | Chat |
| mixtral-8x7b |
Groq
| 32K | $0.27 | $0.27 | $0.0003 | $0.03 | Chat |
| gemma-7b |
Groq
| 8K | $0.1 | $0.1 | $0.0001 | $0.01 | Chat |
| llama-2-7b-chat-fp16 | 
Cloudflare
| 3K | $0.56 | $6.66 | $0.0068 | $0.68 | Chat |
| llama-2-7b-chat-int8 |
Cloudflare
| 2K | $0.16 | $0.24 | $0.0003 | $0.03 | Chat |
| mistral-7b-instruct |
Cloudflare
| 32K | $0.11 | $0.19 | $0.0002 | $0.02 | Chat |
| llama-3-soliloquy-8b | 
Lynn
| 24K | $0.1 | $0.1 | $0.0001 | $0.01 | Chat |
| meta-llama-3-70b-instruct | 
Replicate
| 8K | $0.65 | $2.75 | $0.0029 | $0.29 | Chat |
| meta-llama-3-8b-instruct |
Replicate
| 8K | $0.05 | $0.25 | $0.0003 | $0.03 | Chat |
| llama-2-13b |
Replicate
| 4K | $0.1 | $0.5 | $0.0005 | $0.05 | Chat |
| llama-2-13b |
Replicate
| 4K | $0.1 | $0.5 | $0.0005 | $0.05 | Chat |
| llama-2-7b |
Replicate
| 4K | $0.05 | $0.25 | $0.0003 | $0.03 | Chat |
| llama-2-70b |
Replicate
| 4K | $0.65 | $2.75 | $0.0029 | $0.29 | Chat |
| mistral-7b-v0.1 |
Replicate
| 32K | $0.05 | $0.25 | $0.0003 | $0.03 | Chat |
| mistral-7b-instruct-v0.2 |
Replicate
| 32K | $0.05 | $0.25 | $0.0003 | $0.03 | Chat |
| mixtral-8x7b-instruct-v0.1 |
Replicate
| 32K | $0.3 | $1 | $0.0011 | $0.11 | Chat |
| jurassic-2-ultra | 
AWS
| 32K | $18.8 | $18.8 | $0.0226 | $2.26 | Chat |
| jurassic-2-mid |
AWS
| 32K | $12.5 | $12.5 | $0.015 | $1.5 | Chat |
| titan-text-lite |
AWS
| 32K | $0.3 | $0.4 | $0.0005 | $0.05 | Chat |
| titan-text-express |
AWS
| 32K | $0.8 | $1.6 | $0.0018 | $0.18 | Chat |
| claude-instant |
AWS
| 32K | $0.8 | $2.4 | $0.0026 | $0.26 | Chat |
| claude-3-sonnet |
AWS
| 32K | $3 | $15 | $0.0156 | $1.56 | Chat |
| claude-3-haiku |
AWS
| 32K | $0.25 | $1.25 | $0.0013 | $0.13 | Chat |
| command |
AWS
| 32K | $1.5 | $2 | $0.0023 | $0.23 | Chat |
| command-light |
AWS
| 32K | $0.3 | $0.6 | $0.0007 | $0.07 | Chat |
| llama-2-chat-13b |
AWS
| 32K | $0.75 | $1 | $0.0011 | $0.11 | Chat |
| llama-2-chat-70b |
AWS
| 32K | $1.95 | $2.56 | $0.003 | $0.3 | Chat |
| mistral-7b |
AWS
| 32K | $0.15 | $0.2 | $0.0002 | $0.02 | Chat |
| mistral-8x7b |
AWS
| 32K | $0.45 | $0.7 | $0.0008 | $0.08 | Chat |
| gpt-4-0125-preview |
OpenAI
| 128K | $10 | $30 | $0.032 | $3.2 | Chat |
| gpt-4-1106-preview |
OpenAI
| 128K | $10 | $30 | $0.032 | $3.2 | Chat |
| gpt-4-vision-preview |
OpenAI
| 128K | $10 | $30 | $0.032 | $3.2 | Chat |
| gpt-3.5-turbo-1106 |
OpenAI
| 4K | $1 | $2 | $0.0022 | $0.22 | Chat |
| gpt-3.5-turbo-0613 |
OpenAI
| 4K | $1.5 | $2 | $0.0023 | $0.23 | Chat |
| gpt-3.5-turbo-16k-0613 |
OpenAI
| 4K | $3 | $4 | $0.0046 | $0.46 | Chat |
| gpt-3.5-turbo-0301 |
OpenAI
| 4K | $1.5 | $2 | $0.0023 | $0.23 | Chat |