Replicate LLM API pricing

Every model Replicate serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

40

on this provider

Cheapest input

$0.03

per 1M tokens

Cheapest output

$0.25

per 1M tokens

Max context

1M

tokens

Model ID
Granite 3.3 8B InstructIBM8K$0.03$0.25replicate/ibm-granite/granite-3.3-8b-instruct
Llama 2 7B ChatMeta4K$0.05$0.25replicate/meta/llama-2-7b-chat
Llama 3 8BMeta8K$0.05$0.25replicate/meta/llama-3-8b
Llama 3 8B InstructMeta8K$0.05$0.25replicate/meta/llama-3-8b-instruct
Mistral 7B Instruct V0 2Mistral33K$0.05$0.25replicate/mistralai/mistral-7b-instruct-v0.2
Mistral 7B V0 1Mistral4K$0.05$0.25replicate/mistralai/mistral-7b-v0.1
GPT-5 NanoOpenAI272K$0.05$0.40replicate/openai/gpt-5-nano
Llama 2 7BMeta4K$0.05$0.25replicate/meta/llama-2-7b
gpt-oss-20bOpenAI131K$0.09$0.36replicateopenai/gpt-oss-20b
Llama 2 13BMeta4K$0.10$0.50replicate/meta/llama-2-13b
Llama 2 13B ChatMeta4K$0.10$0.50replicate/meta/llama-2-13b-chat
GPT-4.1 NanoOpenAI1M$0.10$0.40replicate/openai/gpt-4.1-nano
GPT-4o-miniOpenAI131K$0.15$0.60replicate/openai/gpt-4o-mini
gpt-oss-120bOpenAI131K$0.18$0.72replicate/openai/gpt-oss-120b
GPT-5 MiniOpenAI272K$0.25$2.00replicate/openai/gpt-5-mini
Qwen3 235B A22b Instruct 2507Alibaba262K$0.26$1.06replicate/qwen/qwen3-235b-a22b-instruct-2507
Mixtral 8x7B Instruct V0 1Mistral33K$0.30$1.00replicate/mistralai/mixtral-8x7b-instruct-v0.1
GPT-4.1 MiniOpenAI1M$0.40$1.60replicate/openai/gpt-4.1-mini
Llama 2 70BMeta4K$0.65$2.75replicate/meta/llama-2-70b
Llama 3 70BMeta8K$0.65$2.75replicate/meta/llama-3-70b
Llama 3 70B InstructMeta128K$0.65$2.75replicate/meta/llama-3-70b-instruct
Llama 2 70B ChatMeta4K$0.65$2.75replicate/meta/llama-2-70b-chat
DeepSeek V3 1DeepSeek164K$0.67$2.02replicate/deepseek-ai/deepseek-v3.1
Claude 4.5 HaikuAnthropicn/a$1.00$5.00replicate/anthropic/claude-4.5-haiku
o4 MiniOpenAI200K$1.00$4.00replicate/openai/o4-mini
Claude 3.5 HaikuAnthropic200K$1.00$5.00replicate/anthropic/claude-3.5-haiku
O1 MiniOpenAI128K$1.10$4.40replicate/openai/o1-mini
GPT-5OpenAI410K$1.25$10.00replicate/openai/gpt-5
DeepSeekDeepSeek164K$1.45$1.45replicate/deepseek-ai/deepseek-v3
GPT-4.1OpenAI1M$2.00$8.00replicate/openai/gpt-4.1
Gemini 3 ProGoogle1M$2.00$12.00replicate/google/gemini-3-pro
Gemini 2.5 FlashGoogle1M$2.50$2.50replicate/google/gemini-2.5-flash
GPT-4oOpenAI131K$2.50$10.00replicate/openai/gpt-4o
Claude 4 SonnetAnthropic200K$3.00$15.00replicate/anthropic/claude-4-sonnet
Claude 3.7 SonnetAnthropic200K$3.00$15.00replicate/anthropic/claude-3.7-sonnet
Claude 4.5 SonnetAnthropicn/a$3.00$15.00replicate/anthropic/claude-4.5-sonnet
Claude 3.5 SonnetAnthropic200K$3.75$18.75replicate/anthropic/claude-3.5-sonnet
R1DeepSeek164K$3.75$10.00replicate/deepseek-ai/deepseek-r1
Grok 4xAI256K$7.20$36.00replicate/xai/grok-4
o1OpenAI200K$15.00$60.00replicate/openai/o1
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI