How It Works
Two Ways to Access 207+ AI Models
Our unified interface gives you flexible options for working with the latest LLMs
Manual Mode
Select models manually via API. Direct control over which LLM handles your specific requests.
// Example API call with manual model selection
fetch('https://api.redpill.ai/v1/chat/completions', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
model: "openai/o1-mini", // Specify exact model
messages: [{ role: "user", content: "Hello" }]
})
})Best for:
- ✓Specific model benchmarking
- ✓Controlling costs with known models
- ✓Applications requiring consistent outputs
Auto Router Mode
The system dynamically selects the best model based on your query, optimizing for performance and cost.
// Example API call with Auto Router mode
fetch('https://api.redpill.ai/v1/chat/completions', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
mode: "redpill/auto", // Let the system choose
messages: [{ role: "user", content: "Hello" }]
})
})Best for:
- ✓Optimizing cost-performance balance
- ✓Handling varied query types efficiently
- ✓Accessing the latest models automatically
How Our Auto Router Works
See Auto Router in Action
Watch how our system dynamically selects the optimal model for each prompt
Our AI Router selects the optimal model for each specific query, balancing performance and cost
Trending Models
RedPill Auto RouterUpdated 21 days agoDepending on their size, subject, and complexity, your prompts will be routed to the most appropriate AI model from our selection of Claude 3.5, GPT-4o, Llama 3.1/3.3, Mistral, or other models to optimize for both performance and cost-efficiency.
by redpill|200K context|$0/M input tokens|$0/M output tokens- DeepSeek: R1 Distill 70BGPU TEEUpdated 3 months ago
DeepSeek R1 Distill 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1.
by phala|16K context|$0.23/M input tokens|$0.69/M output tokens 
DeepSeek: DeepSeek V3Updated 3 months agoDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.
For model details, please visit for more information, or see the .
by deepseek|64K context|$0.14/M input tokens|$0.28/M output tokens- DeepSeek: DeepSeek R1Updated 3 months ago
DeepSeek R1 is here: Performance on par with , but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.
Fully open-source model & .
MIT licensed: Distill & commercialize freely!
by deepseek|163K context|$7/M input tokens|$7/M output tokens - Meta: Llama 3.3 70B InstructUpdated 5 months ago
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.
Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
by meta-llama|131K context|$0.13/M input tokens|$0.4/M output tokens - Meta: Llama 3.3 70B InstructGPU TEEUpdated 5 months ago
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.
Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
by phala|131K context|$0.12/M input tokens|$0.3/M output tokens
Key Benefits
Unified API For 191+ Models
Access top models like OpenAI, Anthropic and Llama —all in one API.
Best Provider Routing
Auto-routing to the best node for performance and cost.
Pay with Fiat or Crypto
Choose to top up or pay-as-you-go with fiat or crypto.
Open Network
Community-owned, open-source ecosystem.
Use Cases
Custom AI Applications
Build Intelligent Solutions
Create chatbots, data analysis tools, and more with ease.
Scalable AI Solutions
Scale Seamlessly
Adjust your usage as needed without worrying about limitations.
Developer-Friendly
Tools for Innovators
Direct access to all data, tooling, and features through multiple API endpoints.
App Showcases
Questflow
A Collaborative Token-Gated Pragmatic Multi-Agent!
Agent Wars
A Collaborative Token-Gated Pragmatic Multi-Agent!
Jarvis
A Collaborative Token-Gated Pragmatic Multi-Agent!
Open Market
A marketplace that offers a dynamic platform where users can buy and sell datasets, machine learning models, and human labelling services.
Agent Zeta
An autonomous agent designed for financial and crypto research. It provides recommendations and can execute buy actions on-chain.
Electra
A Dapp for Web3 beginners to optimize collateral management and request loans on aave with ease and maximum benefits.
Red Pill API
supports multiple
LLM models
