Run GPT, Claude, Gemini, DeepSeek, and Codex
from one key
Use one key for GPT, Claude, Gemini, DeepSeek, Codex, and image generation across the clients and workflows you already use.
Works seamlessly with your favorite tools
View all
OpenAICodex CLICodex VS CodeCodex app
Continue
Cline
OpenClaw
OpenCode
Kilo Code
Roo Code
Aider
Trae
ZoOpenAICodex CLICodex VS CodeCodex appContinueClineOpenClawOpenCodeKilo CodeRoo CodeAiderTraeZoBuilt for Developers
Everything you need to supercharge your AI coding workflow without the friction.
Real API Keys
Get your own The Claw Bay API key in your dashboard. No shared accounts or borrowed logins.
Faster Regional Routing
Requests are routed across the live regional origin pool, so you're never pinned to a single server.
Universal Compatibility
Works with Codex CLI, Claude Code, Gemini-compatible apps, Continue, Cline, Hermes, Trae, Zo, Aider, and any OpenAI-compatible client.
Instant Setup
Buy access, reveal your key, and start coding. Setup takes less than 2 minutes.
Privacy First
We don't save your chats or read your data. Your code stays yours.
Pay for Usage
Pay for actual headroom instead of jumping to overpriced subscription tiers.
Simple, Transparent Pricing
Pay for usage headroom, not overpriced tiers.
Free Trial
1 hour of access
2 minute setup
Plus
3x GPT Plus headroom
~18K messages/mo
2 minute setup
Codex included
Pro
8x GPT Plus headroom
~55K messages/mo
2 minute setup
Codex included
Ultra
17x GPT Plus headroom
~118K messages/mo
2 minute setup
Codex included
Usage varies by model and prompt size. Cancel anytime.
Prefer to pay per use?
Top up a wallet and spend it down across every model. No tier to pick, no commitment — just balance you control.
Wallet-based billing
Add balance to your account and pay only for what you use. Requests draw from your wallet balance first.
Top-ups never expire
Balance you add manually stays on your account until you spend it — no monthly reset, no forfeited credit.
Optional auto top-up
Subscription renewals can automatically add wallet credit, so heavy workloads keep running without manual refills.
Usage-based, transparent
Spend tracks real usage across every supported model. Watch your balance and history live from your dashboard.
Wallet balance
Your credit, your pace
Quick top-up amounts
Requests use wallet balance first. Subscription renewals add expiring credits, while manual top-ups stay non-expiring.
Top up your walletManage balance and usage from your billing dashboard.
Pay-as-you-go rates
Billed per token, straight from your wallet — premium models at just 10% of official provider pricing, open models at their standard low rates.
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| GPT10% of official | ||
| GPT-5.5 | $0.50 | $3.00 |
| GPT-5.4 | $0.25 | $1.50 |
| GPT-5.4 Mini | $0.125 | $1.00 |
| Claude10% of official | ||
| Claude Opus 4.8 | $0.50 | $2.50 |
| Claude Sonnet 4.6 | $0.30 | $1.50 |
| Claude Haiku 4.5 | $0.10 | $0.50 |
| Gemini10% of official | ||
| Gemini 3 Pro Preview | $0.20 | $1.20 |
| Gemini 3.1 Pro Preview | $0.20 | $1.20 |
| Gemini 3.5 Flash | $0.15 | $0.90 |
| Gemini 2.5 Pro | $0.125 | $1.00 |
| Gemini 3 Flash Preview | $0.05 | $0.30 |
| Gemini 2.5 Flash | $0.03 | $0.25 |
| Gemini 2.5 Flash Lite | $0.01 | $0.04 |
| DeepSeekstandard rate | ||
| DeepSeek V4 Pro Lightning | $0.80 | $1.60 |
| DeepSeek V4 Pro | $0.435 | $0.87 |
| DeepSeek V3.2 | $0.18 | $0.35 |
| DeepSeek V4 Flash | $0.14 | $0.28 |
| GLMstandard rate | ||
| GLM 5.2 | $0.50 | $2.20 |
| GLM 5 | $0.48 | $1.90 |
| GLM 5.1 | $0.45 | $2.15 |
| GLM 4.7 | $0.25 | $1.10 |
| GLM 4.7 Flash | $0.04 | $0.30 |
| Kimistandard rate | ||
| Kimi K2.5 Lightning | $1.00 | $3.00 |
| Kimi K2.7 Code | $0.55 | $2.25 |
| Kimi K2.6 | $0.50 | $1.99 |
| Kimi K2.5 | $0.35 | $1.70 |
| Qwenstandard rate | ||
| Qwen 3.5 397B A17B | $0.35 | $1.75 |
| Qwen 3.6 27B | $0.20 | $1.50 |
| Qwen 3.5 9B | $0.04 | $0.15 |
| MiniMaxstandard rate | ||
| MiniMax M2.5 | $0.11 | $0.95 |
| MiMostandard rate | ||
| Mimo V2.5 Pro | $0.40 | $0.80 |
| Gemmastandard rate | ||
| Gemma 4 31B IT | $0.10 | $0.30 |
Rates apply to standard (uncached) tokens; cached input is billed lower. Output includes any reasoning tokens. Premium-model prices follow official provider list pricing (at 10%) and update with it.
Every model we run, one setup
GPT, Claude, Gemini, DeepSeek, GLM, Kimi, Qwen and more — all reachable from the same account, key, and OpenAI-compatible setup flow.
GPT
OpenAI-compatible GPT models for demanding coding, research, and image generation.
GPT-5.5
gpt-5.5
GPT-5.4
gpt-5.4
GPT-5.4 Mini
gpt-5.4-mini
GPT Image 2
gpt-image-2
Claude
Anthropic Claude models for writing, analysis, and long structured work.
Claude Opus 4.8
claude-opus-4-8
Claude Opus 4.7
claude-opus-4-7
Claude Opus 4.6
claude-opus-4-6
Claude Sonnet 4.6
claude-sonnet-4-6
Claude Haiku 4.5
claude-haiku-4-5
Gemini
Google-family models tuned for fast multimodal and agentic workflows.
Gemini 2.5 Pro
gemini-2.5-pro
Gemini 2.5 Flash
gemini-2.5-flash
Gemini 2.5 Flash Lite
gemini-2.5-flash-lite
Gemini 3 Pro Preview
gemini-3-pro-preview
Gemini 3.1 Pro Preview
gemini-3.1-pro-preview
Gemini 3 Flash Preview
gemini-3-flash-preview
Gemini 3.5 Flash
gemini-3.5-flash
DeepSeek
Large-context DeepSeek models for heavier reasoning at low cost.
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro Lightning
deepseek-v4-pro-lightning
DeepSeek V3.2
deepseek-v3.2
GLM
GLM models with wide context windows for long agent sessions.
GLM 5.2
glm-5.2
GLM 5.1
glm-5.1
GLM 5
glm-5
GLM 4.7
glm-4.7
GLM 4.7 Flash
glm-4.7-flash
Kimi
Kimi models for large-context multimodal coding and research.
Kimi K2.7 Code
kimi-k2.7-code
Kimi K2.6
kimi-k2.6
Kimi K2.5
kimi-k2.5
Kimi K2.5 Lightning
kimi-k2.5-lightning
Qwen & More
Qwen and additional specialist models for broad, lower-cost work.
Mimo V2.5 Pro
mimo-v2.5-pro
Gemma 4 31B IT
gemma-4-31b-it
MiniMax M2.5
minimax-m2.5
Qwen 3.6 27B
qwen3.6-27b
Qwen 3.5 397B A17B
qwen3.5-397b-a17b
Qwen 3.5 9B
qwen3.5-9b
Frequently Asked Questions
Everything you need to know about The Claw Bay.
Want to test the stack before paying?
Join the Discord and claim a free 1-hour trial so you can test latency, compatibility, and workflow fit before committing.
Join Discord