Documentation

Everything you need to integrate Izzi API into your stack.

Getting Started

Install Izzi API in seconds with our auto-configuration tool:

npx izziapi

This command auto-detects your installed tools (Claude Code, Cursor, Cline, Windsurf, Gemini CLI) and configures them to use the Izzi API endpoint.

→ Full install guide|→ OpenClaw GitHub

Authentication

All API requests require an API key. Include it in the header:

Authorization: Bearer izzi-xxxxxxxxxxxx

Get your API key from the dashboard after signing up.

API Endpoints

POST/v1/chat/completions

OpenAI-compatible chat completions endpoint.

curl https://api.izziapi.com/v1/chat/completions \
  -H "Authorization: Bearer izzi-xxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

POST/v1/messages

Claude-compatible messages endpoint (native Anthropic format).

POST/v1/responses

OpenAI Responses API (simplified). See details below.

POST/v1/messages/count_tokens

Pre-count input tokens before making a request.

GET/v1/models

List all available models with pricing info.

GET/v1/models/:id

Lookup a specific model by ID. Supports aliases.

Also available at: /openai/v1/* and /api/v1/*

Responses API

Simplified interface compatible with n8n, LangChain, and other tools using OpenAI's Responses API format.

curl https://api.izziapi.com/v1/responses \
  -H "Authorization: Bearer izzi-xxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "input": "Explain quantum computing in simple terms",
    "instructions": "You are a helpful teacher"
  }'

input — string or array of messages

instructions — system prompt (optional)

stream — enable streaming (optional)

Count Tokens

Pre-count input tokens before making a request — useful for cost estimation.

curl https://api.izziapi.com/v1/messages/count_tokens \
  -H "Authorization: Bearer izzi-xxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

For Claude models, uses native token counting. Other models use local estimation (~4 chars/token).

Extended Thinking

Enable Claude's Extended Thinking for complex reasoning tasks:

curl https://api.izziapi.com/v1/messages \
  -H "x-api-key: izzi-xxxxx" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 16000,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 10000
    },
    "messages": [{"role": "user", "content": "Solve this step by step..."}]
  }'

Supported models: Claude Opus 4/4.6, Claude Sonnet 4/4.5/4.6. The thinking parameter is transparently forwarded.

Rate Limits

Every response includes rate limit headers:

x-ratelimit-tier: pro
x-ratelimit-limit-requests: 60
x-ratelimit-remaining-requests: 47
x-ratelimit-reset-requests: 2026-03-30T00:20:00Z
x-concurrent-limit: 3
x-concurrent-remaining: 2
Retry-After: 60  (only on 429)

Plan	Credits/5h	RPM	Concurrent	Daily
Free	—	10	1	100
Starter ($10/mo)	35	30	2	1,000
Pro ($20/mo) ⭐	80	60	3	2,000
Max ($40/mo)	180	90	6	5,000
Ultra ($80/mo)	400	120	8	10,000

Tool Setup

🟠 Claude Code

# Set environment variables
export ANTHROPIC_BASE_URL=https://api.izziapi.com
export ANTHROPIC_API_KEY=izzi-xxxxx

# Start Claude Code
claude

▶ Cursor

Open Cursor → Settings → Models
Add https://api.izziapi.com/v1 as the OpenAI Base URL
Enter your Izzi API key
Select your preferred model

🌊 Windsurf

export OPENAI_BASE_URL=https://api.izziapi.com/v1
export OPENAI_API_KEY=izzi-xxxxx

🔧 Cline / Aider

export ANTHROPIC_BASE_URL=https://api.izziapi.com
export ANTHROPIC_API_KEY=izzi-xxxxx

Both use Anthropic-format endpoints natively.

✦ Gemini CLI

export OPENAI_BASE_URL=https://api.izziapi.com/v1
export OPENAI_API_KEY=izzi-xxxxx
gemini

OpenClaw Setup

RecommendedGitHub →

One-click setup for OpenClaw with Izzi API. Installs all models, configures provider, verifies API key.

Windows (CMD)

git clone https://github.com/kentzu213/izzi-openclaw.git
cd izzi-openclaw
install.bat izzi-YOUR_KEY_HERE

macOS / Linux (One-liner)

curl -fsSL https://raw.githubusercontent.com/kentzu213/izzi-openclaw/main/install.sh | bash -s -- "izzi-YOUR_KEY_HERE"

VPS / Server (Ubuntu/Debian)

curl -fsSL https://raw.githubusercontent.com/kentzu213/izzi-openclaw/main/install-vps.sh | bash -s -- "izzi-YOUR_KEY_HERE"

After install: restart OpenClaw → select auto · izzi → start chatting!

Supported Models

38 models across 4 tiers. Pricing in USD per 1M tokens. 1 credit = $1.

FREE

Maintained (Free Upstream)

9 models

Ultra-low maintenance fees. Free upstream via Cerebras & OpenRouter.

Model ID	Name	Input	Output	Context
qwen3-235b	Qwen3 235B	$0.08	$0.14	128K
llama-3.3-70b	Llama 3.3 70B	$0.08	$0.14	128K
nemotron-3-super-free	Nemotron 3 Super 120B	$0.08	$0.14	128K
devstral-2-free	Devstral 2 123B	$0.08	$0.14	128K
gemma-3-27b-free	Gemma 3 27B	$0.08	$0.14	96K
llama-3.3-70b-free	Llama 3.3 70B	$0.08	$0.14	128K
openrouter-free	Auto Router	$0.08	$0.14	—
step-3.5-flash	Step 3.5 Flash	$0.075	$0.30	256K
glm-4.5-air	GLM 4.5 Air	$0.075	$0.30	128K

BUDGET

Budget

9 models

Budget-optimized models. Great value for everyday tasks.

Model ID	Name	Input	Output	Context
gpt-5-mini	GPT-5 Mini	$0.35	$2.80	128K
gpt-5.1-mini	GPT-5.1 Mini	$0.44	$3.50	128K
gemini-2.5-flash-lite	Gemini 2.5 Flash Lite	$0.14	$0.83	1M
gpt-4o-mini	GPT-4o Mini	$0.17	$0.66	128K
gpt-5.4-nano	GPT-5.4 Nano	$0.22	$1.38	128K
grok-4.1-fast	Grok 4.1 Fast	$0.23	$0.58	128K
gemini-2.5-flash	Gemini 2.5 Flash	$0.33	$2.75	1M
gpt-4.1-mini	GPT-4.1 Mini	$0.44	$1.76	1M
gpt-5.4-mini	GPT-5.4 Mini	$0.83	$4.95	128K

STANDARD

Standard

9 models

Production-grade models for serious workloads.

Model ID	Name	Input	Output	Context
gpt-5.1	GPT-5.1 ⭐	$0.70	$5.60	128K
gpt-5.1-codex	GPT-5.1 Codex	$0.70	$5.60	128K
auto	Auto Select	$0.70	$5.60	—
claude-haiku-4.5	Claude Haiku 4.5	$0.88	$4.40	200K
gpt-5.1	GPT-5.1	$1.10	$8.80	128K
gpt-5.1-codex	GPT-5.1 Codex	$1.10	$8.80	128K
o3-mini	o3-mini	$1.21	$4.84	128K
gpt-4.1	GPT-4.1	$2.20	$8.80	1M
gpt-4o	GPT-4o	$2.75	$11.00	128K

PREMIUM

Premium

11 models

Flagship models. Claude 4.6, GPT-5.4, Grok 4.

Model ID	Name	Input	Output	Context
gpt-5.2	GPT-5.2	$1.23	$9.80	128K
gemini-2.5-pro	Gemini 2.5 Pro	$1.38	$11.00	1M
gpt-5.4	GPT-5.4	$1.75	$10.50	128K
gpt-5.2-direct	GPT-5.2	$1.93	$15.40	128K
gpt-5.4-direct	GPT-5.4	$2.75	$16.50	272K
claude-sonnet-4.5	Claude Sonnet 4.5	$3.30	$16.50	200K
claude-sonnet-4	Claude Sonnet 4	$3.30	$16.50	200K
claude-sonnet-4.6	Claude Sonnet 4.6 🆕	$3.30	$16.50	200K
grok-4	Grok 4	$3.30	$16.50	256K
claude-opus-4	Claude Opus 4	$5.50	$27.50	200K
claude-opus-4.6	Claude Opus 4.6 🆕	$5.50	$27.50	200K

Error Codes

All errors follow a consistent format:

{
  "error": {
    "type": "rate_limit_error",
    "message": "Rate limit exceeded. Try again in 60 seconds."
  }
}

HTTP	Type	Description
400	invalid_request_error	Malformed request or missing fields
401	authentication_error	Invalid or missing API key
402	insufficient_balance	Not enough credits
403	ip_blocked	IP blocked after too many failed auth attempts
429	rate_limit_error	RPM or concurrent limit exceeded
429	quota_exceeded	Daily request quota exceeded
402	budget_exceeded	Monthly budget limit reached
404	not_found	Model or resource not found
502	upstream_error	Upstream AI provider returned an error
502	connection_error	Failed to reach upstream provider
500	server_error	Internal server error

Payment Methods

1 credit = $1 USD. No expiration on deposited balance.

🏦

Bank Transfer

VND via VietQR

₿

Crypto

BTC, ETH, USDT via Cryptomus

💰

Lolzteam

Marketplace balance

🎁 First deposit bonus: Deposit $1+ → receive +$5 free credits instantly!