LiteLLMModels

Replicate model pricing

As of October 10, 2026, 39 Replicate models are available through LiteLLM. The most recently added are Claude 4.5 Haiku, Claude 4.5 Sonnet, Gemini 3 Pro. Prices below are Replicate's list prices.

How to call Replicate with LiteLLM

Replicate models

ModelLabPriceContextProvidersAdded
Claude 4.5 HaikuAnthropic$1 / $5 per 1M tokens–1Jan 2026
Claude 4.5 SonnetAnthropic$3 / $15 per 1M tokens–1Jan 2026
Gemini 3 ProGoogle$2 / $12 per 1M tokens1M2Jan 2026
Granite 3.3 8B Instruct–$0.03 / $0.25 per 1M tokens8K2Oct 2025
DeepSeek V3.1DeepSeek$0.672 / $2.016 per 1M tokens160K12Aug 2025
GPT OSS 120BOpenAI$0.18 / $0.72 per 1M tokens131K22Aug 2025
GPT OSS 20BOpenAI$0.09 / $0.36 per 1M tokens128K14Aug 2025
GPT-5OpenAI$1.25 / $10 per 1M tokens272K8Aug 2025
GPT-5 MiniOpenAI$0.25 / $2 per 1M tokens272K8Aug 2025
GPT-5 NanoOpenAI$0.05 / $0.40 per 1M tokens272K7Aug 2025
Qwen3 235B A22B Instruct 2507Alibaba$0.264 / $1.06 per 1M tokens128K8Aug 2025
Grok 4xAI$7.20 / $36 per 1M tokens128K4Jul 2025
Claude 4 SonnetAnthropic$3 / $15 per 1M tokens200K5Jun 2025
Gemini 2.5 FlashGoogle$0.30 / $2.50 per 1M tokens1M8Jun 2025
GPT-4.1OpenAI$2 / $8 per 1M tokens1M6Apr 2025
GPT-4.1 MiniOpenAI$0.40 / $1.60 per 1M tokens1M4Apr 2025
GPT-4.1 NanoOpenAI$0.10 / $0.40 per 1M tokens1M4Apr 2025
o4 MiniOpenAI$1 / $4 per 1M tokens200K4Apr 2025
Claude 3.7 SonnetAnthropic$3 / $15 per 1M tokens200K7Feb 2025
DeepSeek R1DeepSeek$3.75 / $10 per 1M tokens64K16Jan 2025
DeepSeek V3DeepSeek$1.45 / $1.45 per 1M tokens64K15Jan 2025
o1OpenAI$15 / $60 per 1M tokens200K4Dec 2024
Claude 3.5 HaikuAnthropic$1 / $5 per 1M tokens200K6Nov 2024
o1 MiniOpenAI$1.10 / $4.40 per 1M tokens128K2Sep 2024
GPT-4o MiniOpenAI$0.15 / $0.60 per 1M tokens128K7Jul 2024
Claude 3.5 SonnetAnthropic$3.75 / $18.75 per 1M tokens200K7Jun 2024
GPT-4oOpenAI$2.50 / $10 per 1M tokens128K7May 2024
Llama 2 13BMeta$0.10 / $0.50 per 1M tokens4K1May 2024
Llama 2 70BMeta$0.65 / $2.75 per 1M tokens4K1May 2024
Llama 2 7BMeta$0.05 / $0.25 per 1M tokens4K1May 2024
Llama 3 70BMeta$0.65 / $2.75 per 1M tokens8K3May 2024
Llama 3 8BMeta$0.05 / $0.25 per 1M tokens8K3May 2024
Llama3 8B InstructMeta$0.05 / $0.25 per 1M tokens8K8May 2024
Mistral 7B Instruct V0.2Mistral AI$0.05 / $0.25 per 1M tokens4K3May 2024
Mistral 7B V0.1Mistral AI$0.05 / $0.25 per 1M tokens4K1May 2024
Llama3 70B InstructMeta$0.65 / $2.75 per 1M tokens8K7Apr 2024
Mixtral 8x7B Instruct V0.1Mistral AI$0.30 / $1 per 1M tokens4K6Jan 2024
Llama 2 13B ChatMeta$0.10 / $0.50 per 1M tokens4K2–
Llama 2 70B ChatMeta$0.65 / $2.75 per 1M tokens4K4–