Sign in
Operated by AI CHAMPION LIMITED

Every leading model. One simple API.

Build coding, office, content, and video products on one OpenAI-compatible endpoint, with clear input, output, and cached-token pricing.

TokenMoo is an independent AI API gateway operated by AI CHAMPION LIMITED. It provides one OpenAI-compatible endpoint for supported text, coding, image, and video models, with published input, output, and cache-read pricing.

Launch pricing: up to 50% off eligible models and periods.

Get your API keyExplore Models
New users get $0.5 in free credit
8B+ tokens served daily23,940+ registered users
OpenAI-compatiblePay as you goLive model pricing

Live model pricing

Choose the right model for every task

View all models
DeepSeek

Featured model

deepseek-v4.1-flash

DeepSeek

50% OFF

Input

$0.3$0.15

Output

$1.2$0.6

Cached input

$0.006$0.003

/ 1M tokens

glm-5.3Input$1.4$0.84Output$4.4$2.64Cached input$0.28$0.168kimi-k3Input$3$1.8Output$15$9Cached input$0.3$0.18
API Base URLhttps://www.tokenmoo.com/v1
32 models, one APIOpenAI-compatibleUp to 50% off
Launch Pricing Active
Up to 50% off model usage
Automatically applied
No promo code required

Popular Models

Compare input, output, and cached-token pricing in one place. Launch pricing is up to 50% off.

View all models

deepseek-v4.1-flash

DeepSeek

50% OFF
Input$0.3$0.15
Output$1.2$0.6
Cached input$0.006$0.003
/ 1M tokens
View pricing

glm-5.3

z-ai

40% OFF
Input$1.4$0.84
Output$4.4$2.64
Cached input$0.28$0.168
/ 1M tokens
View pricing

kimi-k3

Moonshot

40% OFF
Input$3$1.8
Output$15$9
Cached input$0.3$0.18
/ 1M tokens
View pricing

glm-5.3-flash

z-ai

40% OFF
Input$0.15$0.09
Output$0.5$0.3
Cached input$0.03$0.018
/ 1M tokens
View pricing

Use cases

Built for the work you do

Start with a workflow, then choose the model that fits its quality, speed, and budget.

01 / Coding & agents

Ship features faster with an AI pair programmer.

Generate, explain and refactor code across repositories. Switch models without changing your client integration.

  • Generate and refactor code across repositories
  • Run autonomous coding agents
  • Keep prompts portable across models
kimi-k3glm-5.3deepseek-v4.1-flash
02 / Office & productivity

Turn documents and meetings into clear next steps.

Summarize reports, extract action items and draft everyday business writing without switching between providers.

  • Summarize long documents and meeting notes
  • Draft emails, reports and follow-ups
  • Analyze tables and multilingual files
qwen3.8-maxdeepseek-v4-proglm-5.3
03 / Content & localization

Launch in every market without starting over.

Create, rewrite and localize copy from the same endpoint while preserving product terminology and brand voice.

  • Generate marketing and product copy
  • Translate while preserving tone and terminology
  • Run text and image workflows from one account
qwen3.8-maxglm-5.3wan2.7-image
04 / Video generation

Move from brief to video concept in minutes.

Create product demos, social clips and storyboards from prompts or scripts through one API.

  • Turn prompts and scripts into short videos
  • Generate product demos and social clips
  • Coordinate video jobs alongside other workloads
wan3.0-video
1 of 4 workflows
Explore Models

API

Keep your current protocol

Swap the base URL, not your application architecture.

Read API docs

OpenAI Chat

Chat Completions

/v1/chat/completions

OpenAI Responses

Responses API

/v1/responses

Anthropic Messages

Claude-compatible

/v1/messages

Gemini

Generate Content

/v1beta/models/{model}:generateContent

Works with the tools you already use

Connect your favorite IDE, desktop client, or chat interface in minutes.

Setup guides

Compatible with OpenAI, Anthropic, and Gemini request formats.

Service provider and brand relationship

TokenMoo is operated by AI CHAMPION LIMITED

TokenMoo is an independent AI API gateway. It provides API access to supported model services including DeepSeek, Kimi, GLM, Qwen and more, and is not the official website or direct retail service of any model provider. Model names and trademarks belong to their respective owners.

Supported model services: DeepSeek, Kimi, GLM, Qwen and more

Who you buy from

TokenMoo provides the account, billing and support service through AI CHAMPION LIMITED.

What you buy

Usage-based API access to the supported model catalogue through one compatible endpoint.

Brand scope

Provider names describe compatible or supported model services and do not imply official provider affiliation.

Pricing conditions

Rates may vary by model, account group and request time. Review the current model pricing before purchasing.

About TokenMooUser AgreementPrivacy PolicyRefund PolicyContact support

Frequently asked questions

Why route your model traffic through this gateway, how billing works, and what to expect.

Why buy through this gateway instead of each provider directly?

Two practical reasons. Aggregation: one API key and one OpenAI-compatible endpoint give you GLM, Kimi, DeepSeek and other models, so you stop juggling separate accounts, keys and invoices. Payment: you can pay with the local methods shown on the top-up page instead of arranging an overseas card for every provider. Pricing stays transparent — every model price is published on the model square, so you can compare before you spend.

How is pricing calculated?

Usage is billed as you go — per token, with the unit price listed on each model page. You top up a balance and usage is deducted from it.

Which payment methods are supported?

The top-up page lists the channels currently enabled for this site, including local QR-code payments where available. The methods shown there are always the authoritative list.

Can one API key use every model?

Yes. Point any OpenAI-compatible client at this gateway and use the same key. Which models a key can reach depends on the groups your account is allowed to use and the balance available.

Which clients and SDKs work with it?

Anything that speaks the OpenAI or Anthropic protocol works, for example Claude Code, Cline, OpenCode, Kilo Code and Cherry Studio, plus the official SDKs of those ecosystems.

How do I request a refund?

Refund eligibility and the payout window are described in the refund policy; the same page explains how to reach support with your order details.

How is my data handled?

Request handling and account data follow the privacy policy published on this site.

See all modelsRefund PolicyPrivacy PolicyUser Agreement