Impulse
Search…
⌘
K
Models
Providers
Capabilities
Pricing
Compare
API
Playground
Providers
/
Replicate
Visit website
R
Replicate
Inference provider
·
replicate.com
Replicate models via API.
Models
40
Endpoints
3
Regions
1
Avg input
$
1.50
Auth
Bearer token
SDKs
2
Endpoints
POST
/v1/chat/completions
Completions
Stream
POST
/v1/messages
Messages
Stream
POST
/v1/responses
Responses
Stream
Models · 40
Model
Context
Input
Output
Capabilities
gpt-5
0
$
1.25
$
10.00
Vision
Tools
JSON
gpt-5-mini
0
$
0.25
$
2.00
Vision
Tools
JSON
gpt-5-nano
0
$
0.05
$
0.40
Tools
gpt-oss-120b
Open
0
$
0.18
$
0.72
Tools
gpt-oss-20b
Open
0
$
0.09
$
0.36
Tools
gemini-2.5-flash
0
$
2.50
$
2.50
Vision
Tools
JSON
o4-mini
0
$
1.00
$
4.00
Reasoning
gpt-4.1
0
$
2.00
$
8.00
Vision
Tools
JSON
gpt-4.1-mini
0
$
0.40
$
1.60
Vision
Tools
JSON
gpt-4.1-nano
0
$
0.10
$
0.40
Tools
deepseek-r1
Open
66K
$
3.75
$
10.00
Reasoning
o1
0
$
15.00
$
60.00
Reasoning
gpt-4o
0
$
2.50
$
10.00
Vision
Tools
Audio
gpt-4o-mini
0
$
0.15
$
0.60
Vision
Tools
JSON
claude-3.5-haiku
0
$
1.00
$
5.00
Vision
Tools
JSON
claude-3.5-sonnet
0
$
3.75
$
18.75
Vision
Tools
JSON
claude-3.7-sonnet
0
$
3.00
$
15.00
Vision
Tools
JSON
claude-4-sonnet
0
$
3.00
$
15.00
Vision
Tools
JSON
claude-4.5-haiku
0
$
1.00
$
5.00
Vision
Tools
JSON
claude-4.5-sonnet
0
$
3.00
$
15.00
Vision
Tools
JSON
deepseek-v3
Open
66K
$
1.45
$
1.45
Tools
deepseek-v3.1
Open
164K
$
0.67
$
2.02
Reasoning
Tools
gemini-3-pro
0
$
2.00
$
12.00
Vision
Tools
JSON
granite-3.3-8b-instruct
Open
0
$
0.03
$
0.25
Tools
grok-4
0
$
7.20
$
36.00
Tools
llama-2-13b
Open
4K
$
0.10
$
0.50
Tools
llama-2-13b-chat
Open
4K
$
0.10
$
0.50
Tools
llama-2-70b
Open
4K
$
0.65
$
2.75
Tools
llama-2-70b-chat
Open
4K
$
0.65
$
2.75
Tools
llama-2-7b
Open
4K
$
0.05
$
0.25
Tools
llama-2-7b-chat
Open
4K
$
0.05
$
0.25
Tools
llama-3-70b
Open
8K
$
0.65
$
2.75
Tools
llama-3-70b-instruct
Open
8K
$
0.65
$
2.75
Tools
llama-3-8b
Open
8K
$
0.05
$
0.25
Tools
llama-3-8b-instruct
Open
8K
$
0.05
$
0.25
Tools
mistral-7b-instruct-v0.2
Open
4K
$
0.05
$
0.25
Tools
mistral-7b-v0.1
Open
4K
$
0.05
$
0.25
Tools
mixtral-8x7b-instruct-v0.1
Open
4K
$
0.30
$
1.00
Tools
o1-mini
0
$
1.10
$
4.40
Reasoning
qwen3-235b-a22b-instruct-2507
Open
0
$
0.26
$
1.06
Tools
Release timeline
Aug 2025
gpt-oss-120b
Aug 2025
gpt-oss-20b
Aug 2025
gpt-5
Aug 2025
gpt-5-mini
Aug 2025
gpt-5-nano
Details
Category
Inference provider
Website
replicate.com
Auth
Bearer token
Regions
1
Regions
global
SDKs
Python
docs ↗
pip install replicate
TypeScript
docs ↗
npm install replicate