LLMPrice.io

LLM API pricing reference

Published on-demand rates, USD per million tokens, for 42 current first-party text models. Captured 2026-08-10 from public pricing data and committed to our archive.

Cheapest output rate
Ministral 3 3B
$0.100 per 1M out
Widest input to output gap
Gemini 3.5 Flash Lite
output costs 8x its input
Most recent move
Claude Sonnet 5
2026-07-06, input, output and cache
Claude Fable 5Anthropic$10.00$50.00$1.00
Claude Opus 5Anthropic$5.00$25.00$0.500
Claude Sonnet 5Anthropic$2.00$10.00$0.2002026-07-06input, output, cache
Claude Haiku 4.5Anthropic$1.00$5.00$0.100
DeepSeek V4 ProDeepSeek$0.435$0.870$0.004
DeepSeek V4 FlashDeepSeek$0.140$0.280$0.003
Gemini 2.5 ProGoogle$1.25$10.00$0.1252026-01-19cache
Gemini 3.5 FlashGoogle$1.50$9.00$0.150
Gemini 3.6 FlashGoogle$1.50$7.50$0.150
Gemini 3.5 Flash LiteGoogle$0.300$2.50$0.030
Gemini 3.1 Flash LiteGoogle$0.250$1.50$0.025
Gemini 2.5 Flash LiteGoogle$0.100$0.400$0.0102026-01-26cache
Gemini 2.0 Flash Lite 001Google$0.075$0.300$0.019
Magistral Medium 1.2 2509Mistral$2.00$5.00
Mistral Medium 2508Mistral$0.400$2.00
Mistral Large 2512Mistral$0.500$1.50
Codestral 2508Mistral$0.300$0.900
Devstral Small 2512Mistral$0.100$0.300
Ministral 3 14B 2512Mistral$0.200$0.200
Mistral Small 3.2 2506Mistral$0.060$0.180
Ministral 3 8B 2512Mistral$0.150$0.150
Ministral 3 3B 2512Mistral$0.100$0.100
GPT 5.6OpenAI$5.00$30.00$0.500
GPT 5.3OpenAI$1.75$14.00$0.175
GPT 5.6 TerraOpenAI$2.00$12.00$0.200
GPT 5 ChatOpenAI$1.25$10.00$0.125
GPT 5.4 MiniOpenAI$0.750$4.50$0.075
GPT 5 MiniOpenAI$0.250$2.00$0.025
GPT 5.4 NanoOpenAI$0.200$1.25$0.020
GPT 5.6 LunaOpenAI$0.200$1.20$0.020
GPT 5 NanoOpenAI$0.050$0.400$0.005
Sonar ProPerplexity$3.00$15.00
Sonar Reasoning ProPerplexity$2.00$8.00
Sonar ReasoningPerplexity$1.00$5.00
SonarPerplexity$1.00$1.00
Grok 4xAI$3.00$15.00
Grok 4.5xAI$2.00$6.00$0.500
Grok 3 Mini FastxAI$0.600$4.00$0.1502026-02-01cache
Grok 4.3xAI$1.25$2.50$0.200
Grok Code FastxAI$0.200$1.50$0.020
Grok 3 MinixAI$0.300$0.500$0.0752026-02-01cache
Grok 4.1 FastxAI$0.200$0.500$0.050

Rates captured 2026-08-10. Estimates only; confirm on each provider's pricing page. Tap any column heading to sort.

Last change is the day we observed a rate move in our own archive, and which rate moved. An em dash means every rate has held since that model entered the archive. Only 5 of the 42 models here have repriced at all, and most of those moved the cache-read rate rather than input or output, so a change in this column is not the same as a price cut. Dates are observation dates and can lag a provider's announcement.

Price your own workloadCost on your workload, not just the rateHow to compare cheapness honestly

Using one of these figures

Rates on this page were captured 2026-08-10 from each provider's published pricing and committed to our archive, so this reading does not change when a provider edits a page. Quote the date with the number.

LLMPrice.io, “LLM API pricing reference”. Rates captured 2026-08-10. https://llmprice.io/pricing

The same rates as JSON · how the archive works · questions about these numbers