DevKits

LLM API Pricing Comparison (2026)

Input, output, and cached-input prices per 1M tokens, plus context window and max output, for 100+ models across every major provider. Search, filter by provider, and sort by any column to find the cheapest model that fits your context needs.

16 models
ProviderCached in $/1MMax output
Gemini 1.5 FlashGoogle$0.07$0.008K8K
Gemini 2.0 FlashGoogle$0.10$0.40$0.031.0M8K
GPT-4o miniOpenAI$0.15$0.60$0.07128K16K
Claude 3 HaikuAnthropic$0.25$1.25$0.03200K4K
DeepSeek V3 (chat)DeepSeek$0.28$0.42$0.03131K8K
DeepSeek R1 (reasoner)DeepSeek$0.28$0.42$0.03131K66K
CodestralMistral$0.30$0.90$0.03128K128K
Mistral Large 2Mistral$0.50$1.50$0.05262K262K
GPT-3.5 TurboOpenAI$0.50$1.5016K4K
Llama 3.3 70B (Together)Meta$1.04$1.04131K4K
o3-miniOpenAI$1.10$4.40$0.55200K100K
GPT-4oOpenAI$2.50$10.00$1.25128K16K
Llama 3.1 405B (Together)Meta$3.50$3.50131K4K
GPT-4 TurboOpenAI$10.00$30.00128K4K
Claude 3 OpusAnthropic$15.00$75.00$1.50200K4K
o1OpenAI$15.00$60.00$7.50200K100K

Prices in USD per 1M tokens. Source: litellm · last updated Sep 2, 2026, 3:40 AM. Need to estimate a real workload? Use the AI Cost Calculator.