TexAPI

One API key. All AI models. Save 15–50% vs official pricing.

Access Claude, GPT, Gemini, and free models through a single OpenAI-compatible endpoint.
Drop-in replacement for Anthropic, OpenAI, and Google APIs.

---

Getting Started

# That's it. Use any OpenAI-compatible SDK or tool.
curl https://texapi.dev/v1/chat/completions \
  -H "Authorization: Bearer tex-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-4-5", "messages": [{"role": "user", "content": "Hello!"}]}'

1. Sign up → texapi.dev (Google / GitHub / Discord). Get 2 free credits.
2. Create API key → Dashboard → API Keys → Create.
3. Use anywhere → Set base URL to https://texapi.dev/v1 in any OpenAI-compatible tool.

---

Works With Everything

Claude Code export ANTHROPIC_BASE_URL=https://texapi.dev export ANTHROPIC_API_KEY=tex-YOUR_KEY claude	OpenAI Codex CLI export OPENAI_BASE_URL=https://texapi.dev/v1 export OPENAI_API_KEY=tex-YOUR_KEY codex
Gemini CLI export GEMINI_API_BASE=https://texapi.dev/v1 export GEMINI_API_KEY=tex-YOUR_KEY gemini	Any OpenAI SDK from openai import OpenAI client = OpenAI( api_key="tex-YOUR_KEY", base_url="https://texapi.dev/v1" )

Also works with Cursor, Continue, Cline, Aider, LiteLLM, and any tool that accepts a custom OpenAI base URL.

---

Models

💎 Paid Models

Model	Family	Input ($/1M)	Output ($/1M)	Official	Savings
claude-opus-4-7	Claude	$4.25	$21.25	$5 / $25	15% off
claude-opus-4-6	Claude	$4.25	$21.25	$5 / $25	15% off
claude-sonnet-4-6	Claude	$2.55	$12.75	$3 / $15	15% off
claude-haiku-4-5	Claude	$0.85	$4.25	$1 / $5	15% off
gpt-5.5	GPT	$2.50	$15.00	$5 / $30	50% off
gpt-5.4	GPT	$1.25	$7.50	$2.50 / $15	50% off
gpt-5.4-mini	GPT	$0.38	$2.25	$0.75 / $4.50	50% off
gpt-5-codex	GPT	$0.63	$5.00	$1.25 / $10	50% off
o4-mini	GPT	$0.55	$2.20	$1.10 / $4.40	50% off
gemini-2.5-pro	Gemini	$0.75	$6.00	$1.25 / $10	40% off
gpt-image-2	Image	~$0.012 / image		~$0.02–$0.19 / image	~40% off

_{Prices in USD per 1M tokens. Official prices sourced from OpenAI, Anthropic, Google. Full model list at texapi.dev/api/models}

🆓 Free Models

Model	Description	Daily Limit
gpt-oss-120b	120B open-source model	100 – 10,000 req/day
minimax-m2.5-free	MiniMax M2.5	100 – 10,000 req/day
nemotron-3-super-free	NVIDIA Nemotron 3 Super	100 – 10,000 req/day
big-pickle	Big Pickler	100 – 10,000 req/day

_{Free models require one successful payment. Limit scales with plan: No plan (100) → Starter (300) → Builder (1,000) → Pro (3,000) → Business (10,000)}

---

Endpoints

Endpoint	Format	Use with
POST /v1/chat/completions	OpenAI Chat	All models, all tools
POST /v1/messages	Anthropic Messages	Claude Code, native Anthropic SDK
POST /v1/responses	OpenAI Responses	Codex CLI, Responses API
POST /v1/images/generations	OpenAI Images	gpt-image-2
GET /v1/models	OpenAI Models	List available models

---

Pricing

Top-up (Pay-as-you-go)

Amount	Credits	~USD
50,000₫	90	$2
100,000₫	180	$4
200,000₫	360	$8
500,000₫	900	$19
1,000,000₫	1,800	$38

Payment via VietQR (instant bank transfer). International payments coming soon.

Subscription Plans

	Starter	Builder	Pro	Business
Monthly	299,000₫	749,000₫	2,090,000₫	5,290,000₫
Credits	550	1,400	3,900	10,000
RPM	60	240	1,000	3,000
API Keys	3	10	25	100
Free model/day	300	1,000	3,000	10,000

---

How It Works

┌─────────────────────────────────────────────────────────────┐
│  Your App / IDE / CLI                                       │
│  (Claude Code, Codex, Gemini CLI, Cursor, SDK, ...)         │
└─────────────────────┬───────────────────────────────────────┘
                      │ Authorization: Bearer tex-...
                      ▼
┌─────────────────────────────────────────────────────────────┐
│  TexAPI Gateway  (https://texapi.dev/v1)                    │
│                                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌───────────┐  │
│  │ Auth &   │→ │ Rate     │→ │ Credit   │→ │ Smart     │  │
│  │ Key Check│  │ Limiting │  │ Check    │  │ Routing   │  │
│  └──────────┘  └──────────┘  └──────────┘  └─────┬─────┘  │
└───────────────────────────────────────────────────┼─────────┘
                      │ Priority-based fallback      │
          ┌───────────┼───────────┬─────────────────┘
          ▼           ▼           ▼
   ┌────────────┐ ┌────────┐ ┌────────────┐ ┌────────────┐
   │  Claude    │ │  GPT   │ │  Gemini    │ │  Free Pool │
   │ (Anthropic)│ │(OpenAI)│ │ (Google)   │ │ (OSS 120B) │
   └────────────┘ └────────┘ └────────────┘ └────────────┘

Key features:

• 🔀 Smart routing — Priority-based with automatic fallback. If one provider is down, your request goes to the next.
• 🔄 Format translation — Send OpenAI format, get Anthropic response (or vice versa). TexAPI handles conversion.
• 📊 Real-time analytics — Usage per model, per key, per day. Costs, latency, error rates in your dashboard.
• 🔒 Security — Keys hashed (HMAC-SHA256), upstream creds encrypted (AES-256-GCM), zero content storage.
• 💰 Spending controls — Daily cap, per-key monthly limits, real-time balance tracking.
• 🤝 Referral program — Earn 5% commission on every top-up from users you invite. Permanent.

---

Code Examples

Python — Streaming

from openai import OpenAI

client = OpenAI(api_key="tex-YOUR_KEY", base_url="https://texapi.dev/v1")

stream = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Write a Python quicksort"}],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Node.js / TypeScript — Streaming

import OpenAI from "openai";

const client = new OpenAI({ apiKey: "tex-YOUR_KEY", baseURL: "https://texapi.dev/v1" });

const stream = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages: [{ role: "user", content: "Explain async/await in TypeScript" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

cURL — Non-streaming

curl https://texapi.dev/v1/chat/completions \
  -H "Authorization: Bearer tex-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 100
  }'

Anthropic Messages API (native)

curl https://texapi.dev/v1/messages \
  -H "Authorization: Bearer tex-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Explain quantum computing"}]
  }'

---

FAQ

Is my data safe?

Yes. TexAPI does not store any request or response content. Only metadata (token counts, latency, model used) is logged for billing and analytics purposes.

Can I use this in production?

Absolutely. The Business plan supports 3,000 RPM, 100 API keys, and 99.9%+ uptime with multi-provider fallback.

What payment methods are accepted?

VietQR bank transfer (instant) — works with all Vietnamese banks. International payment methods coming soon.

Do credits expire?

Top-up credits never expire. Subscription credits expire at the end of each billing period.

What happens if a provider goes down?

TexAPI automatically routes your request to the next available provider. You don't need to change anything.

---

Documentation

Doc	Description
API Reference	Full endpoint documentation
Setup Claude Code	Use TexAPI with Claude Code
Setup Codex CLI	Use TexAPI with OpenAI Codex
Setup Gemini CLI	Use TexAPI with Gemini CLI
Pricing Comparison	Detailed pricing vs official APIs

---

Links

🌐 texapi.dev · 💬 Discord · 📧 support@texapi.dev

---

_{If TexAPI saves you money, consider giving this repo a ⭐}