Which API formats do you support?

We're compatible with the major model API formats, including OpenAI Chat Completions, Anthropic Messages, and the Gemini API. Developers can reach every supported model through a single, unified API surface.

How are models billed?

Usage is metered by token consumption, with per-model pricing that follows each provider's underlying rate.

Will more models be added over time?

Yes. We continuously onboard new model providers and model families so your stack stays current.

Will my data be used for training or commercial purposes?

No. By default we do not read, store, or use your prompts, responses, or business data for model training or any commercial purpose. The platform only handles API routing, request forwarding, billing, risk control, and reliability.

15% Off Most ModelsUp to 5% Top-up Bonus99.9% API Uptime

AI Models at
Up to 40% Off

One API Key. Every Model.
Access GPT, Claude, Gemini, GLM and more. Pay less, build more.

Get Started for Free Browse Models

5.2

New Model

GLM-5.2
Built to finish.

Our most advanced model for reasoning, agentic workflows, and long-horizon execution.

Explore GLM-5.2

1M Context

Work across large codebases, long documents, and complex knowledge systems.

Long-Horizon Agents

Plan, execute, iterate, and deliver complete outcomes across complex workflows.

Production Ready

Built for real-world applications and enterprise deployment.

Launch Offer

Save 35% on GLM-5.2

Now available at 65% of standard pricing.

View Pricing

Hot Deals

StreamingToolsVision

Fresh AI Models

Explore new launches, all in one place.

Kimi-K3

Long Context · Coding

Featured

GPT-5.6 Series

Reasoning · Coding · Vision

15% Off

GPT-image-2

Image Generation · Editing

15% Off

OpenAI Compatible

Drop-in replacement with zero code changes.

Team Workspace

Manage members and API Keys together.

Model Flexibility

Choose the right model for every use case.

USE CASES

Built for every AI workflow

From side projects to production systems.

Everyday AI Usage

Chat, write, analyze, translate — with any model you need.

Different tasks deserve different models. Access all leading AI models in one place, and switch freely based on what the job calls for.

Pricing

Pay for what you use

Buy credits whenever you need them, and the more you top up, the more bonus credits you get.

Infrastructure

Connected to every major provider

Reliable integrations across every major cloud and inference provider.

          
        us-west-2
eu-central-1
ap-northeast-1
sa-east-1
ap-southeast-2

Hyperscalers

Global Regions

<50ms

P99 Latency

99.99%

Uptime SLA

AWSMicrosoft AzureGoogle CloudAlibaba CloudVolcano EngineTencent Cloud

Models

50+ models, ready to call

One key, every leading model. Auto-synced with the latest official versions.

gpt-4o

gpt-5.3-codex

glm-5.1

veo-3.1-fast-generate-preview

gemini-2.5-flash-image

seed-2.0-pro

gemini-3.1-pro-preview

gemini-3-flash-preview

seedance-2.0

kimi-k2.5

gemini-2.5-pro

happyhorse-1.1-i2v

seed-2.1-pro

claude-opus-4.6

gpt-5.4-mini

qwen3.6-plus

gemini-3.5-flash

glm-5

gpt-5.2-codex

veo-3.1-lite-generate-preview

gpt-5.6-terra

claude-opus-4.8

deepseek-v4-pro

kimi-k3

gemini-2.5-flash

gpt-5.4

gpt-5.4-nano

gpt-5.6-luna

gpt-image-1.5

kimi-k2.6

minimax-m3

glm-5.2

gpt-image-2

qwen3.5-plus

seed-2.0-lite

qwen3.7-max

seedance-2.0-fast

veo-3.1-generate-preview

gpt-5.2

claude-haiku-4.5

claude-opus-4.7

gpt-5.6-sol

happyhorse-1.1-r2v

happyhorse-1.1-t2v

qwen3.5-flash

gpt-5.5

qwen3.7-plus

minimax-m2.5

gpt-5.1-codex

claude-sonnet-4.6

deepseek-v4-flash

glm-5v-turbo

glm-5-turbo

minimax-m2.7

gpt-4o

gpt-5.3-codex

glm-5.1

veo-3.1-fast-generate-preview

gemini-2.5-flash-image

seed-2.0-pro

gemini-3.1-pro-preview

gemini-3-flash-preview

seedance-2.0

kimi-k2.5

gemini-2.5-pro

happyhorse-1.1-i2v

seed-2.1-pro

claude-opus-4.6

gpt-5.4-mini

qwen3.6-plus

gemini-3.5-flash

glm-5

gpt-5.2-codex

veo-3.1-lite-generate-preview

gpt-5.6-terra

claude-opus-4.8

deepseek-v4-pro

kimi-k3

gemini-2.5-flash

gpt-5.4

gpt-5.4-nano

gpt-5.6-luna

gpt-image-1.5

kimi-k2.6

minimax-m3

glm-5.2

gpt-image-2

qwen3.5-plus

seed-2.0-lite

qwen3.7-max

seedance-2.0-fast

veo-3.1-generate-preview

gpt-5.2

claude-haiku-4.5

claude-opus-4.7

gpt-5.6-sol

happyhorse-1.1-r2v

happyhorse-1.1-t2v

qwen3.5-flash

gpt-5.5

qwen3.7-plus

minimax-m2.5

gpt-5.1-codex

claude-sonnet-4.6

deepseek-v4-flash

glm-5v-turbo

glm-5-turbo

minimax-m2.7

seedance-2.0-fast

seed-2.0-lite

glm-5.1

gpt-5.4-nano

qwen3.7-plus

gpt-5.6-sol

minimax-m3

qwen3.5-plus

qwen3.5-flash

gpt-image-1.5

minimax-m2.7

gpt-image-2

kimi-k2.5

gpt-5.4

seedance-2.0

qwen3.7-max

glm-5.2

gemini-2.5-flash-image

gpt-4o

happyhorse-1.1-i2v

gpt-5.4-mini

gemini-2.5-pro

minimax-m2.5

veo-3.1-fast-generate-preview

gpt-5.5

gpt-5.6-terra

gemini-3-flash-preview

glm-5v-turbo

gpt-5.3-codex

happyhorse-1.1-t2v

claude-haiku-4.5

veo-3.1-generate-preview

deepseek-v4-pro

gpt-5.1-codex

happyhorse-1.1-r2v

gemini-3.1-pro-preview

gemini-3.5-flash

claude-opus-4.8

qwen3.6-plus

deepseek-v4-flash

gemini-2.5-flash

gpt-5.2-codex

kimi-k2.6

claude-opus-4.7

glm-5

seed-2.0-pro

claude-opus-4.6

gpt-5.6-luna

claude-sonnet-4.6

gpt-5.2

veo-3.1-lite-generate-preview

kimi-k3

seed-2.1-pro

glm-5-turbo

seedance-2.0-fast

seed-2.0-lite

glm-5.1

gpt-5.4-nano

qwen3.7-plus

gpt-5.6-sol

minimax-m3

qwen3.5-plus

qwen3.5-flash

gpt-image-1.5

minimax-m2.7

gpt-image-2

kimi-k2.5

gpt-5.4

seedance-2.0

qwen3.7-max

glm-5.2

gemini-2.5-flash-image

gpt-4o

happyhorse-1.1-i2v

gpt-5.4-mini

gemini-2.5-pro

minimax-m2.5

veo-3.1-fast-generate-preview

gpt-5.5

gpt-5.6-terra

gemini-3-flash-preview

glm-5v-turbo

gpt-5.3-codex

happyhorse-1.1-t2v

claude-haiku-4.5

veo-3.1-generate-preview

deepseek-v4-pro

gpt-5.1-codex

happyhorse-1.1-r2v

gemini-3.1-pro-preview

gemini-3.5-flash

claude-opus-4.8

qwen3.6-plus

deepseek-v4-flash

gemini-2.5-flash

gpt-5.2-codex

kimi-k2.6

claude-opus-4.7

glm-5

seed-2.0-pro

claude-opus-4.6

gpt-5.6-luna

claude-sonnet-4.6

gpt-5.2

veo-3.1-lite-generate-preview

kimi-k3

seed-2.1-pro

glm-5-turbo

gemini-2.5-flash

gpt-5.4-mini

gpt-5.4

claude-haiku-4.5

gemini-2.5-flash-image

qwen3.6-plus

gpt-image-2

glm-5.2

happyhorse-1.1-i2v

seed-2.0-pro

minimax-m2.7

seedance-2.0-fast

qwen3.7-plus

glm-5.1

glm-5

gpt-image-1.5

happyhorse-1.1-r2v

gpt-5.3-codex

gpt-4o

gpt-5.2-codex

veo-3.1-lite-generate-preview

deepseek-v4-pro

gpt-5.1-codex

happyhorse-1.1-t2v

glm-5v-turbo

gemini-3.1-pro-preview

minimax-m3

veo-3.1-fast-generate-preview

kimi-k3

gpt-5.6-terra

seed-2.1-pro

seed-2.0-lite

deepseek-v4-flash

gemini-3-flash-preview

gpt-5.6-sol

claude-opus-4.7

seedance-2.0

gpt-5.4-nano

gemini-2.5-pro

qwen3.7-max

gpt-5.5

kimi-k2.5

qwen3.5-flash

minimax-m2.5

gpt-5.2

glm-5-turbo

claude-opus-4.6

kimi-k2.6

qwen3.5-plus

gemini-3.5-flash

gpt-5.6-luna

claude-sonnet-4.6

veo-3.1-generate-preview

claude-opus-4.8

gemini-2.5-flash

gpt-5.4-mini

gpt-5.4

claude-haiku-4.5

gemini-2.5-flash-image

qwen3.6-plus

gpt-image-2

glm-5.2

happyhorse-1.1-i2v

seed-2.0-pro

minimax-m2.7

seedance-2.0-fast

qwen3.7-plus

glm-5.1

glm-5

gpt-image-1.5

happyhorse-1.1-r2v

gpt-5.3-codex

gpt-4o

gpt-5.2-codex

veo-3.1-lite-generate-preview

deepseek-v4-pro

gpt-5.1-codex

happyhorse-1.1-t2v

glm-5v-turbo

gemini-3.1-pro-preview

minimax-m3

veo-3.1-fast-generate-preview

kimi-k3

gpt-5.6-terra

seed-2.1-pro

seed-2.0-lite

deepseek-v4-flash

gemini-3-flash-preview

gpt-5.6-sol

claude-opus-4.7

seedance-2.0

gpt-5.4-nano

gemini-2.5-pro

qwen3.7-max

gpt-5.5

kimi-k2.5

qwen3.5-flash

minimax-m2.5

gpt-5.2

glm-5-turbo

claude-opus-4.6

kimi-k2.6

qwen3.5-plus

gemini-3.5-flash

gpt-5.6-luna

claude-sonnet-4.6

veo-3.1-generate-preview

claude-opus-4.8

Browse the full catalog — 50+models →

Why TokenBay

Production-grade by default

Everything you need to ship and scale AI features — without the operational overhead.

OpenAI-compatible API

Pay-as-you-go, No Subscriptions

Transparent, Real-time Billing

Intuitive Developer Console

Access 50+ Models with One API Key

Drop-in Replacement, Zero Code Changes

Multi-Provider Redundancy

Global Low Latency

High Availability Infrastructure

FAQ

Questions, answered.

Can't find what you need? Browse the docs or reach the team.

TokenBay is an AI model API aggregation and routing platform built for developers and enterprises. We provide API aggregation, model routing, unified authentication, unified billing, and risk-control and monitoring capabilities.

Get started in under a minute

Start Building on Global AI
Infrastructure

Get API Key →API Documentation ↗

AI Models at
Up to 40% Off

GLM-5.2
Built to finish.

1M Context

Long-Horizon Agents

Production Ready

Fresh AI Models

Built for every AI workflow

Chat, write, analyze, translate — with any model you need.

Your favorite dev tools, now connected to any model you choose.

Bring AI capabilities into your product or business system.

Run the same task across models and find the one that fits.

Everyone on the team calls the API independently, without stepping on each other.

High concurrency, low latency — your service stays up when it matters.

Pay for what you use

Connected to every major provider

50+ models, ready to call

Production-grade by default

Questions, answered.

Start Building on Global AI
Infrastructure

AI Models atUp to 40% Off

GLM-5.2Built to finish.

1M Context

Long-Horizon Agents

Production Ready

Fresh AI Models

Built for every AI workflow

Chat, write, analyze, translate — with any model you need.

Pay for what you use

Connected to every major provider

50+ models, ready to call

Production-grade by default

Questions, answered.

What kind of platform is TokenBay?+−

Which API formats do you support?+−

How are models billed?+−

Will more models be added over time?+−

Will my data be used for training or commercial purposes?+−

Start Building on Global AIInfrastructure

AI Models at
Up to 40% Off

GLM-5.2
Built to finish.

Start Building on Global AI
Infrastructure