Credit Pricing
Transparent, per-token billing. 1 Credit = 1 USD. All prices shown per 1M tokens.
Cost Calculation Formula
cost = (input_tokens / 1M) × input_price + (output_tokens / 1M) × output_price
Example: A 2,000-token conversation (1,500 input + 500 output) with Claude Sonnet 4 costs ~0.013 credits (~340 VNĐ)
Maintained Models
Free upstream — Izzi charges a small maintenance fee (~2,000 VNĐ / 1M tokens)
| Model | Provider | Size | Input / 1M | Output / 1M |
|---|---|---|---|---|
| LLaMA 4 Maverick 17B | Groq | 17B | $0.08 | $0.14 |
| LLaMA 4 Scout 17B | Groq | 17B | $0.08 | $0.14 |
| LLaMA 3.3 70B | Groq | 70B | $0.08 | $0.14 |
| LLaMA 3.1 8B | Groq | 8B | $0.05 | $0.10 |
| Qwen3 235B | Cerebras | 235B | $0.08 | $0.14 |
| LLaMA 3.3 70B | Cerebras | 70B | $0.08 | $0.14 |
| Qwen3.6 Plus | OpenRouter | — | $0.08 | $0.14 |
| Nemotron 3 Super 120B | OpenRouter | 120B | $0.08 | $0.14 |
| Devstral 2 123B | OpenRouter | 123B | $0.08 | $0.14 |
| Gemma 3 27B | OpenRouter | 27B | $0.08 | $0.14 |
| LLaMA 3.3 70B Free | OpenRouter | 70B | $0.08 | $0.14 |
| Auto Router | OpenRouter | — | $0.08 | $0.14 |
| Step 3.5 Flash | StepFun | — | $0.05 | $0.10 |
| GLM 4.5 Air | Z.ai | — | $0.05 | $0.10 |
| Nemotron 3 Nano 30B | NVIDIA | 30B | $0.08 | $0.14 |
Budget Models
Upstream cost +10% markup — best value for everyday tasks
| Model | Provider | Upstream Price | Izzi Input / 1M | Izzi Output / 1M |
|---|---|---|---|---|
| GPT-4o Mini | OpenAI | $0.15 / $0.60 | $0.165 | $0.660 |
| GPT-4.1 Mini | OpenAI | $0.40 / $1.60 | $0.440 | $1.760 |
| Gemini 2.5 Flash-Lite | $0.13 / $0.75 | $0.143 | $0.825 | |
| Gemini 2.5 Flash | $0.30 / $2.50 | $0.330 | $2.750 | |
| Grok 4.1 Fast | xAI | $0.21 / $0.53 | $0.231 | $0.583 |
Standard Models
Upstream cost +10% markup — balanced performance and quality
| Model | Provider | Upstream Price | Izzi Input / 1M | Izzi Output / 1M |
|---|---|---|---|---|
| Claude Haiku 4.5 | Claude | $0.80 / $4.00 | $0.88 | $4.40 |
| GPT-4.1 | OpenAI | $2.00 / $8.00 | $2.20 | $8.80 |
| GPT-5.1 | OpenAI | $1.00 / $8.00 | $1.10 | $8.80 |
Premium Models
Top-tier models — upstream cost +10% markup
| Model | Provider | Upstream Price | Izzi Input / 1M | Izzi Output / 1M |
|---|---|---|---|---|
| Claude Sonnet 4.6 | Claude | $3.00 / $15.00 | $3.300 | $16.500 |
| Claude Opus 4.6 | Claude | $5.00 / $25.00 | $5.500 | $27.500 |
| Claude Sonnet 4.5 | Claude | $3.00 / $15.00 | $3.300 | $16.500 |
| Claude Sonnet 4 | Claude | $3.00 / $15.00 | $3.300 | $16.500 |
| Claude Opus 4 | Claude | $5.00 / $25.00 | $5.500 | $27.500 |
| GPT-5.4 | OpenAI | $2.50 / $15.00 | $2.750 | $16.500 |
| GPT-5.2 | OpenAI | $1.75 / $14.00 | $1.925 | $15.400 |
| Grok 4 | xAI | $3.00 / $15.00 | $3.300 | $16.500 |
Frequently Asked Questions
What is 1 Credit?
1 Credit = 1 USD ≈ 26,000 VNĐ. First-time deposit of $1 gets you 5 credits (4 bonus credits).
Why are "free" models not free?
Izzi proxies free models through premium infrastructure (Groq, Cerebras, OpenRouter). The maintenance fee ($0.05–$0.08 / 1M tokens) covers server costs, monitoring, and reliability. This is 50–100× cheaper than paid models.
How is the +10% markup calculated?
For paid models (Budget / Standard / Premium), Izzi charges the upstream provider's price × 1.10. This covers API key management, rate limit optimization, failover routing, and 24/7 availability.
Do you offer discounts?
Yes! When Izzi finds cheaper upstream sources (e.g., via optimized routing or alternative providers), we pass the savings to users — up to 50% discount on select models. Check the pricing page for current promotions.
What about cached tokens?
Cached (prompt) tokens are charged at a significantly lower rate than fresh input tokens. This means repeated prompts with the same prefix will cost less over time.