Supported Models - RedPill AI

Overview

RedPill supports 48+ active AI models accessible through a single TEE-protected API across 9 providers. Every request is hardware-protected regardless of which model you choose.

Currently Active: OpenAI, Anthropic, Google, xAI, DeepSeek, Qwen, ZhipuAI, Meta, MoonshotAI, NousResearch, and more

List Models via API

Get the latest models programmatically ->

Model Categories

Chat Models

Conversational AI for chatbots and assistants

Instruction Models

Task completion and code generation

Vision Models

Image understanding and analysis

Embedding Models

Text embeddings for search and similarity

Featured Models

OpenAI Models

Model ID	Context	Prompt	Completion
`openai/gpt-5.2`	400K	$1.75/M	$14/M
`openai/gpt-5.1`	400K	$1.25/M	$10/M
`openai/gpt-5`	400K	$1.25/M	$10/M
`openai/gpt-5-mini`	400K	$0.25/M	$2/M
`openai/gpt-5-nano`	400K	$0.05/M	$0.4/M
`openai/o3`	200K	$2/M	$8/M
`openai/o4-mini`	200K	$1.1/M	$4.4/M
`openai/gpt-4.1`	1M	$2/M	$8/M
`openai/gpt-4.1-mini`	1M	$0.4/M	$1.6/M
`openai/gpt-4.1-nano`	1M	$0.1/M	$0.4/M
`openai/gpt-4o`	128K	$2.5/M	$10/M
`openai/gpt-4o-mini`	128K	$0.15/M	$0.6/M
`openai/gpt-4`	8K	$30/M	$60/M
`openai/gpt-3.5-turbo`	16K	$0.5/M	$1.5/M

New: GPT-5.2 is OpenAI’s latest flagship model with enhanced reasoning and improved performance across all benchmarks.

Anthropic Models

Model ID	Context	Prompt	Completion
`anthropic/claude-opus-4.6`	1M	$10/M	$37.5/M
`anthropic/claude-sonnet-4.6`	1M	$3/M	$15/M
`anthropic/claude-opus-4.5`	200K	$5/M	$25/M
`anthropic/claude-sonnet-4.5`	1M	$3/M	$15/M
`anthropic/claude-opus-4.1`	200K	$15/M	$75/M
`anthropic/claude-opus-4`	200K	$15/M	$75/M
`anthropic/claude-sonnet-4`	1M	$3/M	$15/M
`anthropic/claude-haiku-4.5`	200K	$1/M	$5/M
`anthropic/claude-3.7-sonnet`	200K	$3/M	$15/M
`anthropic/claude-3.5-haiku`	200K	$0.8/M	$4/M

New: Claude Opus 4.6 and Sonnet 4.6 are the latest Anthropic models. Claude Opus 4.5 and Haiku 4.5 are also now available.

Google Models

Model ID	Context	Prompt	Completion
`google/gemini-3-pro-preview`	1M	$4/M	$18/M
`google/gemini-2.5-pro`	1M	$2.5/M	$15/M
`google/gemini-2.5-flash`	1M	$0.3/M	$2.5/M
`google/gemini-2.5-flash-lite`	1M	$0.1/M	$0.4/M

New: Gemini 3 Pro Preview is Google’s next-generation model with advanced reasoning capabilities. Gemini 2.5 Pro pricing updated to $2.5/M prompt.

xAI Models

Model ID	Context	Prompt	Completion
`x-ai/grok-4`	256K	$3/M	$15/M
`x-ai/grok-4.1-fast`	2M	$0.2/M	$0.5/M
`x-ai/grok-code-fast-1`	256K	$0.2/M	$1.5/M

New: Grok 4.1 Fast now supports a massive 2M token context window at just $0.2/M prompt.

DeepSeek Models

Model ID	Context	Prompt	Completion	Provider
`deepseek/deepseek-v3.2`	163K	$0.27/M	$0.4/M	Chutes
`deepseek/deepseek-chat-v3.1`	163K	$1/M	$2.5/M	Near AI
`deepseek/deepseek-r1-0528`	163K	$2/M	$2/M	Tinfoil

New: DeepSeek V3.2 is the latest version available through Chutes. DeepSeek R1 is a reasoning model available with Tinfoil TEE protection.

MoonshotAI Models

Model ID	Context	Prompt	Completion	Provider
`moonshotai/kimi-k2.5`	262K	$0.6/M	$3/M	Chutes
`moonshotai/kimi-k2-thinking`	262K	$2/M	$2/M	Tinfoil

New: Kimi K2.5 is a native multimodal model with state-of-the-art visual coding. Kimi K2 Thinking is an advanced reasoning model optimized for long-horizon agentic tasks.

Qwen Models

Model ID	Context	Prompt	Completion	Provider
`qwen/qwen3-coder-480b-a35b-instruct`	262K	$2/M	$2/M	Tinfoil
`qwen/qwen3-vl-30b-a3b-instruct`	128K	$0.2/M	$0.7/M	Phala
`qwen/qwen3-30b-a3b-instruct-2507`	262K	$0.15/M	$0.45/M	Near AI
`qwen/qwen-2.5-7b-instruct`	32K	$0.04/M	$0.1/M	Phala

ZhipuAI Models

Model ID	Context	Prompt	Completion	Provider
`z-ai/glm-5`	202K	$1.2/M	$3.5/M	Phala
`z-ai/glm-4.7`	131K	$0.85/M	$3.3/M	Near AI
`z-ai/glm-4.7-flash`	202K	$0.1/M	$0.43/M	Phala

New: GLM-5 is ZhipuAI’s latest flagship model for systems engineering. GLM 4.7 Flash offers excellent speed-to-quality ratio with 202K context.

Other Models

Model ID	Context	Prompt	Completion	Provider
`openai/gpt-oss-120b`	131K	$0.1/M	$0.49/M	Phala
`openai/gpt-oss-20b`	131K	$0.04/M	$0.15/M	Phala
`google/gemma-3-27b-it`	53K	$0.11/M	$0.4/M	Phala
`meta-llama/llama-3.3-70b-instruct`	131K	$2/M	$2/M	Tinfoil
`nousresearch/hermes-3-llama-3.1-405b`	131K	$1/M	$1/M	OpenRouter
`phala/uncensored-24b`	32K	$0.2/M	$0.9/M	Phala

GPU TEE Confidential Models

RedPill offers 17 confidential AI models running entirely in GPU TEE across 4 providers:

Phala Network (8 models)

Model ID	Context	Prompt	Completion
`phala/glm-5`	202K	$1.2/M	$3.5/M
`phala/gpt-oss-120b`	131K	$0.1/M	$0.49/M
`phala/qwen3-vl-30b-a3b-instruct`	128K	$0.2/M	$0.7/M
`phala/gemma-3-27b-it`	53K	$0.11/M	$0.4/M
`phala/uncensored-24b`	32K	$0.2/M	$0.9/M
`phala/gpt-oss-20b`	131K	$0.04/M	$0.15/M
`phala/glm-4.7-flash`	202K	$0.1/M	$0.43/M
`phala/qwen-2.5-7b-instruct`	32K	$0.04/M	$0.1/M

Tinfoil (4 models)

Model ID	Context	Prompt	Completion
`deepseek/deepseek-r1-0528`	163K	$2/M	$2/M
`qwen/qwen3-coder-480b-a35b-instruct`	262K	$2/M	$2/M
`moonshotai/kimi-k2-thinking`	262K	$2/M	$2/M
`meta-llama/llama-3.3-70b-instruct`	131K	$2/M	$2/M

Near AI (3 models)

Model ID	Context	Prompt	Completion
`deepseek/deepseek-chat-v3.1`	163K	$1/M	$2.5/M
`qwen/qwen3-30b-a3b-instruct-2507`	262K	$0.15/M	$0.45/M
`z-ai/glm-4.7`	131K	$0.85/M	$3.3/M

Chutes (2 models)

Model ID	Context	Prompt	Completion
`deepseek/deepseek-v3.2`	163K	$0.27/M	$0.4/M
`moonshotai/kimi-k2.5`	262K	$0.6/M	$3/M

Learn About Confidential AI

Explore all 17 GPU TEE models in detail ->

Vision Models

Models that understand images:

Model ID	Context	Features	Provider
`phala/qwen3-vl-30b-a3b-instruct`	128K	Vision + Text	Phala
`phala/gemma-3-27b-it`	53K	Vision + Text	Phala
`moonshotai/kimi-k2.5`	262K	Vision + Text	Chutes

Embedding Models

Generate vector embeddings for semantic search:

Model ID	Dimensions	Max Tokens
`openai/text-embedding-3-large`	3072	8191
`openai/text-embedding-3-small`	1536	8191
`openai/text-embedding-ada-002`	1536	8191

Provider Coverage

Supported Providers

OpenAI - GPT-5.2, GPT-5.1, GPT-5, GPT-4.1, O3, O4-mini, GPT-OSS, embeddings
Anthropic - Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Opus 4.1, Claude Haiku 4.5, Claude 3.7 Sonnet, Claude 3.5 Haiku
Google - Gemini 3 Pro Preview, Gemini 2.5 Pro/Flash/Flash-Lite
xAI - Grok 4, Grok 4.1 Fast, Grok Code Fast
DeepSeek - DeepSeek V3.2, DeepSeek V3.1, DeepSeek R1
MoonshotAI - Kimi K2.5, Kimi K2 Thinking
Qwen - Qwen3 Coder 480B, Qwen3 VL, Qwen3 30B, Qwen 2.5
ZhipuAI - GLM-5, GLM-4.7, GLM-4.7 Flash
Meta - Llama 3.3 70B
NousResearch - Hermes 3 Llama 405B

Pricing Tiers

Budget Models

Balance of cost and quality:

phala/qwen-2.5-7b-instruct - $0.04/M prompt (TEE)
phala/gpt-oss-20b - $0.04/M prompt (TEE)
openai/gpt-5-nano - $0.05/M prompt
phala/glm-4.7-flash - $0.1/M prompt (TEE)
google/gemini-2.5-flash-lite - $0.1/M prompt
openai/gpt-4o-mini - $0.15/M prompt

Mid-Range Models

Production-ready with strong quality:

openai/gpt-5-mini - $0.25/M prompt
google/gemini-2.5-flash - $0.3/M prompt
moonshotai/kimi-k2.5 - $0.6/M prompt
anthropic/claude-3.5-haiku - $0.8/M prompt

Premium Models

Best quality for production:

openai/gpt-5.2 - $1.75/M prompt
anthropic/claude-sonnet-4.5 - $3/M prompt
google/gemini-2.5-pro - $2.5/M prompt
anthropic/claude-opus-4.6 - $10/M prompt

Model Selection Guide

By Use Case

Chatbots & Assistants

Best: anthropic/claude-sonnet-4.5, openai/gpt-5Budget: openai/gpt-5-mini, phala/qwen-2.5-7b-instruct

Code Generation

Best: openai/gpt-5, anthropic/claude-opus-4.6Budget: x-ai/grok-code-fast-1, phala/glm-4.7-flash

Text Analysis

Best: anthropic/claude-sonnet-4.5, google/gemini-2.5-proBudget: google/gemini-2.5-flash, phala/qwen-2.5-7b-instruct

Image Understanding

Best: phala/qwen3-vl-30b-a3b-instruct, moonshotai/kimi-k2.5Budget: phala/gemma-3-27b-it

High-Privacy Workloads

TEE-Protected: All Phala models

phala/glm-5 - Best quality
phala/gpt-oss-120b - OpenAI architecture
phala/qwen-2.5-7b-instruct - Budget option

Long Context

Best: x-ai/grok-4.1-fast (2M tokens), google/gemini-2.5-pro (1M tokens), anthropic/claude-opus-4.6 (1M tokens)TEE: phala/glm-5 (202K tokens), phala/glm-4.7-flash (202K tokens)

Agentic / Reasoning

Best: moonshotai/kimi-k2-thinking, deepseek/deepseek-r1-0528, openai/o3Budget: phala/glm-4.7-flash, openai/o4-mini

Get Latest Models

Via API

# All models
curl https://api.redpill.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

# Phala confidential models only
curl https://api.redpill.ai/v1/models/phala \
  -H "Authorization: Bearer YOUR_API_KEY"

Via SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.redpill.ai/v1"
)

# List all models
models = client.models.list()
for model in models.data:
    print(f"{model.id}")

# Filter for TEE models
import requests
resp = requests.get(
    "https://api.redpill.ai/v1/models",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)
for model in resp.json()["data"]:
    if "phala" in model.get("providers", []):
        print(f"TEE: {model['id']}")

Model Properties

Each model includes:

Property	Description
`id`	Model identifier for API calls
`name`	Human-readable name
`context_length`	Maximum tokens in context window
`pricing.prompt`	Cost per token (prompt)
`pricing.completion`	Cost per token (completion)
`input_modalities`	Input types (text, image, file, audio)
`output_modalities`	Output types (text)
`providers`	Array of infrastructure providers (phala, tinfoil, near-ai, etc.)
`metadata.appid`	Phala TEE application ID (for attestation)

Model Compatibility

OpenAI SDK Compatible

All models work with OpenAI SDK:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.redpill.ai/v1"
)

# Use any model
response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.5",
    messages=[{"role": "user", "content": "Hello"}]
)

Streaming Support

All chat models support streaming:

stream = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.5",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True
)

Function Calling

Supported models:

All OpenAI GPT models
Anthropic Claude 3+ models
Google Gemini models
Meta Llama 3.2+ models
Phala GLM and GPT-OSS models

FAQs

Are all models protected by TEE?

Yes! All requests flow through the TEE-protected gateway, regardless of model. For end-to-end TEE protection (including model inference), use Phala, Tinfoil, Near AI, or Chutes confidential models.

How do I identify which models run on Phala?

Three ways: (1) Use the /v1/models/phala endpoint, (2) check the providers field for "phala", or (3) use the phala/ prefix in model IDs.

What's the difference between regular and TEE models?

Regular models: TEE-protected gateway only (your request is protected in transit)TEE models (Phala/Tinfoil/Near AI/Chutes): Full end-to-end TEE (gateway + inference in GPU TEE)

How often are new models added?

We add new models regularly. Check the API or docs for the latest additions.

Can I request a specific model?

Yes! Email support@redpill.ai with your model request.

Next Steps

Start Using Models

Make your first request

Confidential AI Models

Explore all TEE models in detail

API Reference

Models API endpoint

Pricing Details

Understand pricing

RedPill Chat

​Overview

List Models via API

​Model Categories

Chat Models

Instruction Models

Vision Models

Embedding Models

​Featured Models

​OpenAI Models

​Anthropic Models

​Google Models

​xAI Models

​DeepSeek Models

​MoonshotAI Models

​Qwen Models

​ZhipuAI Models

​Other Models

​GPU TEE Confidential Models

​Phala Network (8 models)

​Tinfoil (4 models)

​Near AI (3 models)

​Chutes (2 models)

Learn About Confidential AI

​Vision Models

​Embedding Models

​Provider Coverage

​Supported Providers

​Pricing Tiers

​Budget Models

​Mid-Range Models

​Premium Models

​Model Selection Guide

​By Use Case

​Get Latest Models

​Via API

​Via SDK

​Model Properties

​Model Compatibility

​OpenAI SDK Compatible

​Streaming Support

​Function Calling

​FAQs

​Next Steps

Start Using Models

Confidential AI Models

API Reference

Pricing Details

Overview

Model Categories

Featured Models

OpenAI Models

Anthropic Models

Google Models

xAI Models

DeepSeek Models

MoonshotAI Models

Qwen Models

ZhipuAI Models

Other Models

GPU TEE Confidential Models

Phala Network (8 models)

Tinfoil (4 models)

Near AI (3 models)

Chutes (2 models)

Vision Models

Embedding Models

Provider Coverage

Supported Providers

Pricing Tiers

Budget Models

Mid-Range Models

Premium Models

Model Selection Guide

By Use Case

Get Latest Models

Via API

Via SDK

Model Properties

Model Compatibility

OpenAI SDK Compatible

Streaming Support

Function Calling

FAQs

Next Steps