tokentab

Replicate API Pricing 2026

Replicate runs open-source models in the cloud with a simple API. Pay per second of compute time.

Showing 40 models from Replicate. Prices are per 1 million tokens. Data sourced from official pricing pages via LiteLLM.

Models

40

Cheapest Input

$0.03

/1M tokens

Cheapest Output

$0.25

/1M tokens

Max Context

164K

tokens

40 models
Features
ibm-granite/granite-3.3-8b-instruct$0.030$0.250——
meta/llama-2-7b$0.050$0.2504.1K4.1K
meta/llama-2-7b-chat$0.050$0.2504.1K4.1K
meta/llama-3-8b$0.050$0.2508.1K8.1K
meta/llama-3-8b-instruct$0.050$0.2508.1K8.1K
mistralai/mistral-7b-instruct-v0.2$0.050$0.2504.1K4.1K
mistralai/mistral-7b-v0.1$0.050$0.2504.1K4.1K
openai/gpt-5-nano$0.050$0.400——
gpt-oss-20b$0.090$0.360——
meta/llama-2-13b$0.100$0.5004.1K4.1K
meta/llama-2-13b-chat$0.100$0.5004.1K4.1K
openai/gpt-4.1-nano$0.100$0.400——
openai/gpt-4o-mini$0.150$0.600——
openai/gpt-oss-120b$0.180$0.720——
openai/gpt-5-mini$0.250$2.00——
qwen/qwen3-235b-a22b-instruct-2507$0.264$1.06——
mistralai/mixtral-8x7b-instruct-v0.1$0.300$1.004.1K4.1K
openai/gpt-4.1-mini$0.400$1.60——
meta/llama-2-70b$0.650$2.754.1K4.1K
meta/llama-2-70b-chat$0.650$2.754.1K4.1K
meta/llama-3-70b$0.650$2.758.2K8.2K
meta/llama-3-70b-instruct$0.650$2.758.2K8.2K
deepseek-ai/deepseek-v3.1$0.672$2.02163.8K163.8K
anthropic/claude-3.5-haiku$1.00$5.00——
anthropic/claude-4.5-haiku$1.00$5.00——
openai/o4-mini$1.00$4.00——
openai/o1-mini$1.10$4.40——
openai/gpt-5$1.25$10.00——
deepseek-ai/deepseek-v3$1.45$1.4565.5K8.2K
google/gemini-3-pro$2.00$12.00——
openai/gpt-4.1$2.00$8.00——
google/gemini-2.5-flash$2.50$2.50——
openai/gpt-4o$2.50$10.00——
anthropic/claude-3.7-sonnet$3.00$15.00——
anthropic/claude-4-sonnet$3.00$15.00——
anthropic/claude-4.5-sonnet$3.00$15.00——
anthropic/claude-3.5-sonnet$3.75$18.75——
deepseek-ai/deepseek-r1$3.75$10.0065.5K8.2K
xai/grok-4$7.20$36.00——
openai/o1$15.00$60.00——

Actualización Semanal de Precios LLM

Recibe notificaciones cuando cambien los precios de modelos IA. Gratis, sin spam, cancela cuando quieras.