RE

Replicate

Serverless Featured

Run and deploy machine learning models with a cloud API. Pay-per-use with serverless GPU infrastructure.

Features

OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode

Compliance

SOC 2
HIPAA
GDPR

Pricing Model

per token

Details

Models 68
API Base https://api.replicate.com
GPU CloudImage GenerationLLM InferenceVideo Generation

Model Catalog (68)

Model Type Input $/1M Output $/1M Context Speed Status
Claude 3.5 Haiku
Anthropic
llm $1.00 $5.00 — —
Claude 4.5 Haiku
Anthropic
llm $1.00 $5.00 — —
Claude 4.5 Sonnet
Anthropic
llm $3.00 $15.00 — —
Claude 4.6 Opus
Anthropic
llm $5.00 $25.00 — —
Claude 4.6 Sonnet
Anthropic
llm $3.00 $15.00 — —
DeepSeek R1
DeepSeek · 671B MoE
llm $3.75 $10.00 — —
DeepSeek V3
DeepSeek · 671B MoE
llm $1.45 $1.45 — —
DeepSeek V3.1
DeepSeek · 671B MoE
llm $0.672 $2.02 — —
Dream Machine
Luma AI
video gen $0.019/req — — —
Eleven Music
ElevenLabs
music gen $8.30/req — — —
Flash V2.5
ElevenLabs
text to_speech $0.050/req — — —
Flux 1 Dev
Black Forest Labs
image gen $0.025/img — — —
Flux 1 Pro
Black Forest Labs
image gen $0.055/img — — —
Flux 1 Schnell
Black Forest Labs
image gen $0.0030/img — — —
Flux 1.1 Pro
Black Forest Labs
image gen $0.040/img — — —
Flux 1.1 Pro Ultra
Black Forest Labs
image gen $0.060/img — — —
Flux 2 Dev
Black Forest Labs
image gen $0.012/img — — —
Flux 2 Flex
Black Forest Labs
image gen $0.060/img — — —
Flux 2 Max
Black Forest Labs
image gen $0.030/img — — —
Flux 2 Pro
Black Forest Labs
image gen $0.015/img — — —
Flux Kontext Pro
Black Forest Labs
image gen $0.040/img — — —
GPT Image 1.5
OpenAI
image gen $0.013/img — — —
GPT-4o
OpenAI
llm $2.50 $10.00 — —
GPT-4o Mini
OpenAI
llm $0.150 $0.600 — —
GPT-5 Mini
OpenAI
llm $0.250 $2.00 — —
GPT-5 Nano
OpenAI
llm $0.050 $0.400 — —
GPT-5.2
OpenAI
llm $1.75 $14.00 — —
GPT-5.4
OpenAI
llm $1.25 $10.00 — —
Gemini 2.5 Flash
Google
llm $0.300 $2.50 — —
Gemini 2.5 Flash Image
Google
image gen $0.039/img — — —
Gemini 3 Flash
Google
llm $0.500 $3.00 — —
Gemini 3 Pro
Google
llm $2.00 $4.00 — —
Gemini 3 Pro Image
Google
image gen $0.035/img — — —
Gemini 3.1 Flash Image
Google
image gen $0.067/img — — —
Gemini 3.1 Flash Lite Image
Google
image gen $0.034/img — — —
Gemini 3.1 Pro
Google
llm $2.00 $4.00 — —
Gen-4.5
Runway
video gen $0.120/sec — — —
Grok 4
xAI
llm $7.20 $36.00 — —
Grok Aurora
xAI
image gen $0.020/img — — —
Grok Aurora
xAI
image gen $0.050/sec — — —
Hailuo 2.3
MiniMax
video gen $0.280/req — — —
Ideogram 2.0
Ideogram
image gen $0.080/img — — —
Ideogram 3.0
Ideogram
image gen $0.090/img — — —
Ideogram Character
Ideogram
image gen $0.100/img — — —
Imagen 4
Google
image gen $0.040/img — — —
Imagen 4 Fast
Google
image gen $0.020/img — — —
Imagen 4 Ultra
Google
image gen $0.060/img — — —
Kling 2.1
Kuaishou
video gen $0.050/sec — — —
Kling 2.6
Kuaishou
video gen $0.070/sec — — —
Kling 3.0
Kuaishou
video gen $0.168/sec — — —
Lyria 3
Google
music gen $0.040/req — — —
Lyria 3 Pro
Google
music gen $0.080/req — — —
Music 2.5
MiniMax
music gen $0.030/req — — —
Recraft V3
Recraft
image gen $0.040/img — — —
Seedance 1.0
ByteDance
video gen $0.030/sec — — —
Seedream 3.0
ByteDance
image gen $0.030/img — — —
Seedream 4.0
ByteDance
image gen $0.030/img — — —
Seedream 4.5
ByteDance
image gen $0.040/img — — —
Seedream 5.0 Lite
ByteDance
image gen $0.035/img — — —
Speech 2.6
MiniMax
text to_speech $0.060/req — — —
Stable Diffusion 3.5 Medium
Stability AI
image gen $0.035/img — — —
Veo 3
Google
video gen $0.400/sec — — —
Veo 3.1
Google
video gen $0.400/sec — — —
Wan 2.5
Alibaba
video gen $0.050/sec — — —
Wan 2.7 Image
Alibaba
image gen $0.030/img — — —
Wan 2.7 Image Pro
Alibaba
image gen $0.030/img — — —
Wan 2.7 Video
Alibaba
video gen $0.100/sec — — —
o4 Mini
OpenAI
llm $1.00 $4.00 — —

Replicate API FAQ

Is the Replicate API free?

Not as far as we track: Replicate has no free API tier on record. The cheapest option we track is GPT-5 Nano at $0.05 in / $0.40 out per 1M tokens.

What is the cheapest Replicate model?

GPT-5 Nano at $0.05 in / $0.40 out per 1M tokens, based on the 68 models we track for Replicate.

How many models does Replicate offer?

We track 68 Replicate models: 31 image generation, 20 LLM, 11 video generation, 4 music, 2 text-to-speech.