Tokens
1 /mo
Gemini 1.5 flash-8b pricing
Variant: 128k context
Context windows size:
1000 ksmallest model for lower intelligence use cases
Per million tokens
Input:
$0.0375Output:
$0.15Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$02 /mo
Gemini 2.0 Flash-Lite pricing
Variant: 1m context
Context windows size:
1000 ksmallest and most cost effective model
Per million tokens
Input:
$0.075Output:
$0.3Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$02 /mo
Gemini 1.5 flash pricing
Variant: 128k context
Context windows size:
128 kfastest model for repetitive tasks
Per million tokens
Input:
$0.075Output:
$0.3Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$03 /mo
Gemini 2.0 Flash pricing
Variant: 1m context
Context windows size:
1000 kmost capable multi-modal model
Per million tokens
Input:
$0.1Output:
$0.4Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$03 /mo
Jamba 1.5 pricing
Variant: Mini
Context windows size:
256 kEfficient & lightweight
Per million tokens
Input:
$0.2Output:
$0.4Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$04 /mo
Gemini 1.5 flash pricing
Variant: 1 mill context
Context windows size:
1000 kfastest model for repetitive tasks
Per million tokens
Input:
$0.15Output:
$0.6Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$04 /mo
Command R pricing
Variant:
Context windows size:
128 koptimized for long context tasks
Per million tokens
Input:
$0.15Output:
$0.6Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$05 /mo
GPT-4o mini pricing
Variant:
Context windows size:
128 kcost-efficient small model
Per million tokens
Input:
$0.15Output:
$0.6Input Batch:
$0.75Output Batch:
$0.3Cached input:
$0.075Cached output:
$05 /mo
GPT-4o mini pricing
Variant: 2024-07-18
Context windows size:
128 kcost-efficient small model
Per million tokens
Input:
$0.15Output:
$0.6Input Batch:
$0.75Output Batch:
$0.3Cached input:
$0.075Cached output:
$06 /mo
Gemini 1.5 flash-8b pricing
Variant: 1 mill context
Context windows size:
1000 ksmallest model for lower intelligence use cases
Per million tokens
Input:
$0.75Output:
$0.3Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$07 /mo
deepseek-chat pricing
Variant: DeepSeek-V3
Context windows size:
64 kPer million tokens
Input:
$0.27Output:
$1.1Input Batch:
$0Output Batch:
$0Cached input:
$0.07Cached output:
$08 /mo
Command R pricing
Variant: Fine-tuned
Context windows size:
128 koptimized for long context tasks
Per million tokens
Input:
$0.3Output:
$1.2Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$012 /mo
deepseek-reasoner pricing
Variant: DeepSeek-R1
Context windows size:
64 kPer million tokens
Input:
$0.14Output:
$2.19Input Batch:
$0Output Batch:
$0Cached input:
$0.14Cached output:
$025 /mo
Claude 3.5 pricing
Variant: Haiku
Context windows size:
200 kFastest, most cost-effective model
Per million tokens
Input:
$0.8Output:
$4Input Batch:
$0.4Output Batch:
$2Cached input:
$1Cached output:
$0.0829 /mo
o3-mini pricing
Variant: o3
Context windows size:
200 kcost-efficient small model
Per million tokens
Input:
$1.1Output:
$4.4Input Batch:
$0.55Output Batch:
$2.2Cached input:
$0.55Cached output:
$032 /mo
Gemini 1.5 pro pricing
Variant: 128k context
Context windows size:
128 knext-gen model
Per million tokens
Input:
$1.25Output:
$5Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$050 /mo
Jamba 1.5 pricing
Variant: Large
Context windows size:
256 kpowerful long context model
Per million tokens
Input:
$2Output:
$8Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$060 /mo
Grok 2 pricing
Variant:
Context windows size:
128 kPer million tokens
Input:
$2Output:
$10Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$063 /mo
Gemini 1.5 pro pricing
Variant:
Context windows size:
2000 knext-gen model
Per million tokens
Input:
$2.5Output:
$10Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$063 /mo
Gemini 1.0 pro pricing
Variant:
Context windows size:
2000 kfirst gen model for text and image
Per million tokens
Input:
$2.5Output:
$10Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$063 /mo
Command R+ pricing
Variant:
Context windows size:
128 kmost powerful, scalable large language model
Per million tokens
Input:
$2.5Output:
$10Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$065 /mo
GPT-4o pricing
Variant:
Context windows size:
128 kTheir most advanced multimodal model
Per million tokens
Input:
$2.5Output:
$10Input Batch:
$1.25Output Batch:
$5Cached input:
$1.25Cached output:
$065 /mo
GPT-4o pricing
Variant: 2024-11-20
Context windows size:
128 kTheir most advanced multimodal model
Per million tokens
Input:
$2.5Output:
$10Input Batch:
$1.25Output Batch:
$5Cached input:
$1.25Cached output:
$065 /mo
GPT-4o pricing
Variant: 2024-08-06
Context windows size:
128 kGPT-4o with improved reasoning capabilities
Per million tokens
Input:
$2.5Output:
$10Input Batch:
$1.25Output Batch:
$5Cached input:
$1.25Cached output:
$075 /mo
OpenAI o1-mini pricing
Variant:
Context windows size:
128 kfast, cost-efficient tailored to coding, math, and science
Per million tokens
Input:
$3Output:
$12Input Batch:
$0Output Batch:
$0Cached input:
$1.5Cached output:
$075 /mo
OpenAI o1-mini pricing
Variant: 2024-09-12
Context windows size:
128 kfast, cost-efficient tailored to coding, math, and science
Per million tokens
Input:
$3Output:
$12Input Batch:
$0Output Batch:
$0Cached input:
$1.5Cached output:
$093 /mo
Claude 3.7 pricing
Variant: Sonnet
Context windows size:
200 kmost intelligent model
Per million tokens
Input:
$3Output:
$15Input Batch:
$1.5Output Batch:
$7.5Cached input:
$3.75Cached output:
$0.393 /mo
Claude 3.5 pricing
Variant: Sonnet
Context windows size:
200 kintelligent model
Per million tokens
Input:
$3Output:
$15Input Batch:
$1.5Output Batch:
$7.5Cached input:
$3.75Cached output:
$0.3103 /mo
GPT-4o pricing
Variant: 2024-05-13
Context windows size:
128 kGPT-4o with improved reasoning capabilities
Per million tokens
Input:
$5Output:
$15Input Batch:
$2.5Output Batch:
$7.5Cached input:
$0Cached output:
$0375 /mo
OpenAI o1-preview pricing
Variant:
Context windows size:
128 kreasoning model for complex tasks
Per million tokens
Input:
$15Output:
$60Input Batch:
$0Output Batch:
$0Cached input:
$7.5Cached output:
$0375 /mo
OpenAI o1-preview pricing
Variant: 2024-09-12
Context windows size:
128 kreasoning model for complex tasks
Per million tokens
Input:
$15Output:
$60Input Batch:
$0Output Batch:
$0Cached input:
$7.5Cached output:
$0385 /mo
o1 pricing
Variant:
Context windows size:
200 kFrontier reasoning model
Per million tokens
Input:
$15Output:
$60Input Batch:
$7.5Output Batch:
$30Cached input:
$7.5Cached output:
$0462 /mo
Claude 3 pricing
Variant: Opus
Context windows size:
200 kPowerful model for complex tasks
Per million tokens
Input:
$15Output:
$75Input Batch:
$7.5Output Batch:
$37.5Cached input:
$18.75Cached output:
$1.51154 /mo
GPT-4.5 pricing
Variant:
Context windows size:
128 kLargest GPT model
Per million tokens
Input:
$75Output:
$150Input Batch:
$37.5Output Batch:
$75Cached input:
$37.5Cached output:
$01500 /mo
GPT-4o pricing
Variant: audio-preview
Context windows size:
128 kGPT-4o with audio capabilities
Per million tokens
Input:
$100Output:
$200Input Batch:
$0Output Batch:
$0Cached input:
$0Cached output:
$0LLM pricing comparison is not too hard to figure out, the newest models are usually pretty expensive, so give the last generation models a try to see if you can get away with a cheaper price.
The LLM pricing calculator works with large numbers, all the inputs usually take a million or more requests per box to start showing the real price.
This is an estimation tool only.The actual bill could be very different. SaaS Pricing is not responsible for any miscalculations. The prices and terms may be wrong, and may be changed. If no region is specified, you can assume it's Frankfurt, Germany. SaaS Prices is not affiliated with the providers in the calculators, unless explicitly stated.