Consensus Protocol API

Consensus Protocol serves open-weight large language models on dedicated GPU hardware it operates, via an OpenAI-compatible inference API.

Get startedTry in LoungeVisit company

Data & Privacy

HQ:US
Safety identifier:Not forwarded
API Training:No
Prompt Logging:No
Retention:0 days
Inference data handling
Terms of Service
|Privacy Policy

Available Models

DeepSeek V4.1 Flash

deepseek
deepseek-v4.1-flash
Streaming
Vision
Tools
Reasoning
Consensus Protocol
Context: 1.0M
Input
$0.15
/M tokens
Cached
$0.005
/M tokens
Output
$0.55
/M tokens
Get Started

Qwen3.8 27B

Qwen3.8 27B
Qwen3.8-27B
Streaming
Vision
Tools
Reasoning
Consensus Protocol
Context: 262k
Input
$0.08
/M tokens
Cached
$0.05
/M tokens
Output
$0.35
/M tokens
Get Started

GLM-5.3 Flash

zai
glm-5.3-flash
Streaming
Vision
Tools
Reasoning
Consensus Protocol
Context: 1.0M
Input
$0.1
/M tokens
Cached
$0.02
/M tokens
Output
$0.25
/M tokens
Get Started

DeepSeek V4 Flash

deepseek
deepseek-v4-flash
Streaming
Tools
Reasoning
JSON Output
Consensus Protocol
Context: 524.3k
Input
$0.1
/M tokens
Cached
$0.005
/M tokens
Output
$0.2
/M tokens
Get Started

Gemma 4 31B IT

google
gemma-4-31b-it
Streaming
Tools
Reasoning
Consensus Protocol
Context: 262.1k
Input
$0.1
/M tokens
Cached
$0.01
/M tokens
Output
$0.25
/M tokens
Get Started

GPT OSS 20B

openai
gpt-oss-20b
Streaming
Tools
Reasoning
JSON Output
Consensus Protocol
Context: 128kQuant: fp4
Input
$0.04
/M tokens
Cached
$0.01
/M tokens
Output
$0.19
/M tokens
Get Started

FAQ

Consensus Protocol API questions

Can't find an answer? Contact us

Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to deepseek-v4.1-flash. On pay-as-you-go keys, consensusprotocol/deepseek-v4.1-flash pins every request to Consensus Protocol; DevPass coding plans do not support provider pinning. You do not need a separate Consensus Protocol account or SDK.