Full-chain token visibility, visual billing

ModelGo is more than model aggregation — it's an enterprise AI usage governance platform

One API to reach mainstream models — billing detail, usage dashboards, and access guardrails, all in one place.

$
One Access Point

Integrate once. Access many models.

Compatible with OpenAI and Anthropic APIs — switch models with one base_url, no code rewrites. Works with DeepSeek, Qwen, Zhipu BigModel and major overseas models.

O
OpenAI
GPT-4o · o3 · o4-mini
A
Anthropic
Claude Opus · Sonnet · Haiku
G
Google
Gemini 2.5 Pro · Flash
D
DeepSeek
R1 · V3 · Coder
D
Doubao
Pro · Lite · Vision
Q
Qwen
Qwen3 · VL · Coder
O
OpenAI
GPT-4o · o3 · o4-mini
A
Anthropic
Claude Opus · Sonnet · Haiku
G
Google
Gemini 2.5 Pro · Flash
D
DeepSeek
R1 · V3 · Coder
D
Doubao
Pro · Lite · Vision
Q
Qwen
Qwen3 · VL · Coder
M
Moonshot
Kimi k2 · k1.5
M
Mistral
Large · Nemo · Codestral
M
Meta
Llama 4 · Llama 3.3
Z
Zhipu
GLM-4 · CogVideo · CogView
B
Baichuan
Baichuan4 · Turbo
M
MiniMax
Text · Speech · Video
M
Moonshot
Kimi k2 · k1.5
M
Mistral
Large · Nemo · Codestral
M
Meta
Llama 4 · Llama 3.3
Z
Zhipu
GLM-4 · CogVideo · CogView
B
Baichuan
Baichuan4 · Turbo
M
MiniMax
Text · Speech · Video
Fine-grained billing · Usage governance

From a single call to company-wide usage governance

Token-level pricing + project-level budget control + multi-layer cost breakdown — your enterprise AI spend, managed in one place.

Token-level pricing

Priced in separate buckets for input, output and cache — every charge traceable and reconcilable line by line.

Project-level budget control

Budget caps per workspace, spend caps per key — over-limit calls are blocked on the spot.

Multi-layer cost breakdown

Break spend down by account / workspace / key — allocation at a glance, every entry reconcilable.

USAGE & LOGS

Full observability dashboard, integrate with your existing stack

Complete usage dashboards and call logs — spend / requests / tokens tri-view, trends and distributions at a glance. Filter by model, status, key, and inspect raw payloads. Forward to Datadog, OpenTelemetry, and more.

Spend / Requests / Tokens dashboard — trends and distributions at a glance
Filter logs by model, status, or key — inspect raw request/response payloads
Forward logs to Datadog, OpenTelemetry, and more — unified observability stack
ENTERPRISE MULTI-TENANCY

Permission system that scales with your team

From a solo developer's single account to enterprise multi-org, multi-workspace, multi-member — three-layer identity and two-layer roles scale smoothly. Add people, delegate permissions, spin up projects — no rebuild required.

SAFETY GUARDRAILS

Every call stays within allowed boundaries

Safety guardrails (model blocklist / IP allowlist / member restrictions) + default policies + key bindings. Keep models and sources within your enterprise's approved scope.

Model blocklist

Restrict which models can be called — unauthorized ones are blocked outright.

IP allowlist

Restrict call sources — only trusted addresses get through.

Key-bound policies

Bind different guardrails to different keys. Default policies apply instantly.

QUICK START

Standard protocol, no project rework needed

OpenAI / Anthropic compatible — swap base_url and key, done. cURL / Python / Node examples included, first call in minutes.

Python
Compatible withOpenAIAnthropicAzure OpenAI
COMMAND LINE · CLI

CLI integration into your dev workflow

ModelGo CLI lets you log in and check balance from the terminal, inject skills into major AI clients with one command.

Claude Code
Cursor
Trae
$ npx @model-go/cli@latest install
# Install and inject clients in one line
$ modelgo auth login
# Terminal login
$ modelgo wallet balance
# Check balance

Bring AI usage under enterprise governance

Availability target ≥ 99.5%