01gate — One gateway. Every frontier model.

Model Catalog

Frontier Models & Transparent Rates

Direct 50% discount off official provider pricing with enterprise uptime, persistent prompt-caching, and zero KYC requirements.

OpenAI • Flagship 1M Context

gpt-6-astra

Apex flagship neural engine. Supreme reasoning, complex system architecture synthesis, and autonomous agent coordination.

Input / 1M:$5.00

Output / 1M:$25.00

Prompt Cache:$0.50 (90% off)

OpenAI • Standard 1M Context

gpt-6.1-sol

Next-gen Sol architecture. Ideal balance of deep intelligence, sub-second execution, and cost efficiency for production code.

Input / 1M:$1.00

Output / 1M:$5.00

Prompt Cache:$0.05 (95% off)

OpenAI • Vision & Code 1M Context

gpt-6.1-terra

Optimized mid-tier intelligence for advanced visual reasoning, tool use, and computer tasks with high cost efficiency.

Input / 1M:$0.50

Output / 1M:$2.50

Prompt Cache:$0.025 (95% off)

OpenAI 1M Context

gpt-6-luna

Ultra-fast low-latency frontier intelligence. Near-instant token generation designed for real-time autocomplete and high-QPS tasks.

Input / 1M:$0.05

Output / 1M:$0.25

Prompt Cache:$0.005 (90% off)

Anthropic 1M Context

claude-opus-5-5

Heavyweight logic, architectural synthesis, and deep multi-step planning with native thinking reasoning blocks.

Input / 1M:$2.00

Output / 1M:$10.00

Prompt Cache:$0.10 (95% off)

Anthropic • Premium 1M Context

claude-sonnet-5-5

Balanced engineering tier for autonomous coding, refactoring, and multi-file software architecture at peak throughput.

Input / 1M:$1.00

Output / 1M:$5.00

Prompt Cache:$0.10 (90% off)

Anthropic • Fast 1M Context

claude-sonnet-5

Ultra-high-throughput Sonnet 5 architecture optimized for automated programming, code reviews, and fast multi-turn tasks.

Input / 1M:$1.00

Output / 1M:$5.00

Prompt Cache:$0.10 (90% off)

Anthropic • Fable 1M Context

claude-fable-5-1

Next-gen reasoning and high-velocity code generation architecture built for dynamic tasks and deep context workflows.

Input / 1M:$0.75

Output / 1M:$3.00

Prompt Cache:$0.075 (90% off)

Anthropic 1M Context

claude-haiku-5-5

Fast, lightweight Anthropic model for high-throughput classification, extraction, and everyday automation.

Input / 1M:$0.05

Output / 1M:$0.25

Prompt Cache:$0.005 (90% off)

DeepSeek • Flash 1M Context

deepseek-v4.1-flash

Native multimodal Flash model for lightning-fast agents, code synthesis, tool calls, and high-velocity reasoning.

Input / 1M:$0.05

Output / 1M:$0.20

Prompt Cache:$0.005 (90% off)

Z.AI 1M Context

glm-5.3

Flagship reasoning model for complex software engineering and long-horizon agent workflows, with always-on thinking and tool use.

Input / 1M:$0.25

Output / 1M:$1.00

Prompt Cache:$0.025 (90% off)

Z.AI 1M Context

glm-5.3-flash

High-speed reasoning model combining deep thinking tokens with rapid generation for responsive coding assistants.

Input / 1M:$0.05

Output / 1M:$0.20

Prompt Cache:$0.005 (90% off)

Google • Argon Frontier 1M+ Context

gemini-4-argon

Google's flagship Argon reasoning intelligence with deep multimodal synthesis, code architecture, and ultra-low latency.

Input / 1M:$0.75

Output / 1M:$3.00

Prompt Cache:$0.075 (90% off)

Google 1M+ Context

gemini-3.8-flash

Ultra-responsive multimodal powerhouse with built-in thinking reasoning and million-token document recall capabilities.

Input / 1M:$0.375

Output / 1M:$1.875

Prompt Cache:$0.038 (90% off)

xAI 500K Context

grok-4.7

Elite architectural reasoning and code generation with massive real-time context comprehension and minimal hallucination rates.

Input / 1M:$1.00

Output / 1M:$3.00

Prompt Cache:$0.25 (75% off)

Integration

Connect to Your Favorite Tools

Drop-in replacement for OpenAI API across every major IDE, CLI agent, and SDK. Select your application below for instant setup.

1. Open Settings: Navigate to Cursor Settings → Models → OpenAI API Key.

2. Override Base URL: Enable Override OpenAI Base URL and enter:
https://api.01gate.com/v1

3. Enter API Key: Paste your personal token sk-01gate-...

4. Add Target Models: gpt-6-astra, gpt-6.1-sol, gpt-6.1-terra, claude-sonnet-5-5, grok-4.7, deepseek-v4.1-flash.

💡 Pro-tip: Use gpt-6.1-sol or claude-sonnet-5-5 for day-to-day coding, and switch to gpt-6-astra or grok-4.7 for complex architectural design.

# Cursor IDE Configuration Base URL: https://api.01gate.com/v1 API Key: sk-01gate-your-token # Active Models to Add: • gpt-6-astra (OpenAI Flagship, 1M ctx) • gpt-6.1-sol (OpenAI Workhorse, 1M ctx) • claude-sonnet-5-5 (Anthropic Refactor, 1M ctx) • claude-opus-5-5 (Anthropic Deep Logic, 1M ctx) • grok-4.7 (xAI Reasoning, 500K ctx) • deepseek-v4.1-flash (River Reasoning, 1M ctx) • gemini-3.8-flash (Google Speed, 1M+ ctx)

1. Install Extension: Install Continue, Roo Code, or Cline from VS Code Marketplace.

2. Select Provider: Choose OpenAI-compatible (Custom OpenAI) in provider settings.

3. Base URL: https://api.01gate.com/v1

4. API Key: Enter your token sk-01gate-...

5. Set Default Model: Recommend gpt-6.1-sol or claude-sonnet-5-5.

// settings.json (Continue / Roo / Cline) { "models": [ { "title": "01gate - GPT 6.1 Sol", "provider": "openai", "model": "gpt-6.1-sol", "apiBase": "https://api.01gate.com/v1", "apiKey": "sk-01gate-your-token" } ] }

1. Edit config.toml: Open ~/.codex/config.toml (Windows: %USERPROFILE%\.codex\config.toml).

2. Configure Provider: Add 01gate with wire_api = "responses".

3. Set auth.json: Place your key into ~/.codex/auth.json.

4. Launch: Run codex in terminal with full 1M context window support.

# ~/.codex/config.toml model_provider = "01gate" model = "gpt-6.1-sol" model_reasoning_effort = "high" disable_response_storage = true [model_providers.01gate] name = "01gate" base_url = "https://api.01gate.com" wire_api = "responses" requires_openai_auth = true # ~/.codex/auth.json { "OPENAI_API_KEY": "sk-01gate-your-token" }

1. Launch in Terminal: Export environment variables and run official Claude Code CLI.

2. Persistent Config: Save directly to ~/.claude/settings.json.

3. Switch Models Live: Change models inside chat via /model claude-sonnet-5-5 or /model claude-opus-5-5.

# PowerShell (Windows): $env:ANTHROPIC_BASE_URL="https://api.01gate.com" $env:ANTHROPIC_AUTH_TOKEN="sk-01gate-your-token" $env:CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC="1" claude # macOS / Linux (Bash/Zsh): export ANTHROPIC_BASE_URL="https://api.01gate.com" export ANTHROPIC_AUTH_TOKEN="sk-01gate-your-token" claude

1. Configuration File: Open ~/.config/opencode/opencode.json.

2. Dual-Provider Support: Set up both OpenAI and Anthropic pipelines routed to 01gate.

3. Instant Switching: Seamlessly toggle between gpt-6-astra, gpt-6.1-sol, and claude-sonnet-5-5.

// opencode.json { "provider": { "openai": { "options": { "baseURL": "https://api.01gate.com/v1", "apiKey": "sk-01gate-your-token" }, "models": { "gpt-6-astra": { "name": "GPT 6 Astra" }, "gpt-6.1-sol": { "name": "GPT 6.1 Sol" } } } } }

1. Config Setup: In ~/.hermes/config.yaml set provider: custom pointing to 01gate.

2. API Key: In ~/.hermes/.env set OPENAI_API_KEY=sk-01gate-....

3. Autonomous Run: Launch hermes to run your autonomous agent.

# ~/.hermes/config.yaml model: provider: custom default: gpt-6.1-sol base_url: https://api.01gate.com/v1 api_mode: chat_completions # ~/.hermes/.env OPENAI_API_KEY=sk-01gate-your-token

1. High-Performance Reasoning: Use deepseek-v4.1-flash and glm-5.3-flash for lightning-fast coding and agentic loops.

2. Drop-in OpenAI API: Configure any client with base URL https://api.01gate.com/v1.

3. Unbeatable Cost: Up to 50% cheaper with full reasoning and tool calling support.

# Python OpenAI SDK from openai import OpenAI client = OpenAI( base_url="https://api.01gate.com/v1", api_key="sk-01gate-your-token" ) res = client.chat.completions.create( model="deepseek-v4.1-flash", # or glm-5.3-flash messages=[{"role": "user", "content": "Write a high-performance Redis cache layer."}], stream=True )

1. Grok CLI: Configure ~/.grok/config.toml to route Grok 4.7 through 01gate.

2. Elite Reasoning: Run Grok 4.7 with full 500K context window.

# ~/.grok/config.toml [models] default = "grok" [model."grok"] model = "grok-4.7" base_url = "https://api.01gate.com/v1" api_key = "sk-01gate-your-token" api_backend = "responses" context_window = 500000

1. Open Settings: Go to Settings → Provider → OpenAI.

2. Base URL: https://api.01gate.com/v1

3. API Key: Enter your token sk-01gate-...

4. Full Model Access: Add gpt-6-astra, gpt-6.1-sol, gpt-6.1-terra, claude-sonnet-5-5, grok-4.7, deepseek-v4.1-flash, gemini-3.8-flash.

# Cherry Studio / NextChat / Chatbox Provider: OpenAI Compatible Base URL: https://api.01gate.com/v1 API Key: sk-01gate-your-token # Available models: • gpt-6-astra • gpt-6.1-sol • claude-sonnet-5-5 • grok-4.7 • deepseek-v4.1-flash • glm-5.3-flash • gemini-3.8-flash

1. Python OpenAI SDK: Use the standard openai package, just set base_url.

2. Anthropic SDK: Native anthropic library pointing to base URL https://api.01gate.com.

3. Direct cURL: Instant HTTP requests from any backend or CLI script.

from openai import OpenAI client = OpenAI( base_url="https://api.01gate.com/v1", api_key="sk-01gate-your-token" ) res = client.chat.completions.create( model="gpt-6-astra", messages=[{"role": "user", "content": "Hello 01gate!"}], stream=True )

One gateway. Every frontier model.

Frontier Models & Transparent Rates

Connect to Your Favorite Tools

Instant API Access via Telegram

One gateway.
Every frontier model.