inference cloud

Replicate

Models, pricing and feature compatibility available through Replicate.

Deployments

40

Models

40

Labs

9

With pricing

40

Models on Replicate

Follow any model to compare this deployment with the same model through other providers.

ModelProvider model IDModeRegionInputOutputContextTools
Claude Haiku 3.5anthropic/claude-3.5-haikuChatglobal$1.00 / 1M$5.00 / 1Msupported
Claude Sonnet 3.5anthropic/claude-3.5-sonnetChatglobal$3.75 / 1M$18.75 / 1Msupported
Claude Sonnet 3.7anthropic/claude-3.7-sonnetChatglobal$3.00 / 1M$15.00 / 1Msupported
Claude Haiku 4.5anthropic/claude-4.5-haikuChatglobal$1.00 / 1M$5.00 / 1Msupported
Claude Sonnet 4.5anthropic/claude-4.5-sonnetChatglobal$3.00 / 1M$15.00 / 1Msupported
Claude Sonnet 4anthropic/claude-4-sonnetChatglobal$3.00 / 1M$15.00 / 1Msupported
DeepSeek-Ai Deepseek R1deepseek-ai/deepseek-r1Chatglobal$3.75 / 1M$10.00 / 1M65.5Kunknown
DeepSeek-Ai Deepseekdeepseek-ai/deepseek-v3Chatglobal$1.45 / 1M$1.45 / 1M65.5Ksupported
DeepSeek-Ai Deepseek V3 1deepseek-ai/deepseek-v3.1Chatglobal$0.67 / 1M$2.02 / 1M163.8Ksupported
Gemini 2.5 Flashgoogle/gemini-2.5-flashChatglobal$2.50 / 1M$2.50 / 1Msupported
Gemini 3 Progoogle/gemini-3-proChatglobal$2.00 / 1M$12.00 / 1Msupported
Ibm Granite Granite 3 3 8B Instructibm-granite/granite-3.3-8b-instructChatglobal$0.03 / 1M$0.25 / 1Msupported
Llama 2 13Bmeta/llama-2-13bChatglobal$0.10 / 1M$0.50 / 1M4.1Kunknown
Llama 2 13B Chatmeta/llama-2-13b-chatChatglobal$0.10 / 1M$0.50 / 1M4.1Kunknown
Llama 2 70Bmeta/llama-2-70bChatglobal$0.65 / 1M$2.75 / 1M4.1Kunknown
Llama 2 70B Chatmeta/llama-2-70b-chatChatglobal$0.65 / 1M$2.75 / 1M4.1Kunknown
Llama 2 7Bmeta/llama-2-7bChatglobal$0.05 / 1M$0.25 / 1M4.1Kunknown
Llama 2 7B Chatmeta/llama-2-7b-chatChatglobal$0.05 / 1M$0.25 / 1M4.1Kunknown
Llama 3 70Bmeta/llama-3-70bChatglobal$0.65 / 1M$2.75 / 1M8.2Kunknown
Llama 3 70B Instructmeta/llama-3-70b-instructChatglobal$0.65 / 1M$2.75 / 1M8.2Kunknown
Llama 3 8Bmeta/llama-3-8bChatglobal$0.05 / 1M$0.25 / 1M8.1Kunknown
Llama 3 8B Instructmeta/llama-3-8b-instructChatglobal$0.05 / 1M$0.25 / 1M8.1Kunknown
Mistralai Mistral 7B Instruct V0 2mistralai/mistral-7b-instruct-v0.2Chatglobal$0.05 / 1M$0.25 / 1M4.1Kunknown
Mistralai Mistral 7B V0 1mistralai/mistral-7b-v0.1Chatglobal$0.05 / 1M$0.25 / 1M4.1Kunknown
Mistralai Mixtral 8x7B Instruct V0 1mistralai/mixtral-8x7b-instruct-v0.1Chatglobal$0.30 / 1M$1.00 / 1M4.1Kunknown
GPT-4.1openai/gpt-4.1Chatglobal$2.00 / 1M$8.00 / 1Msupported
GPT-4.1 miniopenai/gpt-4.1-miniChatglobal$0.40 / 1M$1.60 / 1Msupported
GPT-4.1 nanoopenai/gpt-4.1-nanoChatglobal$0.10 / 1M$0.40 / 1Msupported
GPT-4oopenai/gpt-4oChatglobal$2.50 / 1M$10.00 / 1Msupported
GPT-4o miniopenai/gpt-4o-miniChatglobal$0.15 / 1M$0.60 / 1Msupported
GPT-5openai/gpt-5Chatglobal$1.25 / 1M$10.00 / 1Msupported
GPT-5 miniopenai/gpt-5-miniChatglobal$0.25 / 1M$2.00 / 1Msupported
GPT-5 nanoopenai/gpt-5-nanoChatglobal$0.05 / 1M$0.40 / 1Msupported
gpt-oss-120bopenai/gpt-oss-120bChatglobal$0.18 / 1M$0.72 / 1Msupported
o1openai/o1Chatglobal$15.00 / 1M$60.00 / 1Munknown
o1-miniopenai/o1-miniChatglobal$1.10 / 1M$4.40 / 1Munknown
o4-miniopenai/o4-miniChatglobal$1.00 / 1M$4.00 / 1Munknown
Qwen Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-instruct-2507Chatglobal$0.26 / 1M$1.06 / 1Msupported
Replicateopenai Gpt Oss 20Breplicateopenai/gpt-oss-20bChatglobal$0.09 / 1M$0.36 / 1Msupported
Grok 4xai/grok-4Chatglobal$7.20 / 1M$36.00 / 1Msupported

Labs available through Replicate