IzziAI

Credit Pricing

Transparent, per-token billing. 1 Credit = 1 USD = 26,300 VND by default. All prices shown per 1M tokens.

Cost Calculation Formula

cost = (uncached_input / 1M) × input_price + (cached_input / 1M) × cache_price + (output / 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

Maintained Models

Free upstream — Izzi charges a small maintenance fee (~2,000 VNĐ / 1M tokens)

ModelProviderSizeInput / 1MOutput / 1M
Qwen3 235BCerebras235B$0.08$0.14
LLaMA 3.3 70BCerebras70B$0.08$0.14
LLaMA 3.1 405BSambaNova405B$0.08$0.14
DeepSeek R1SambaNova671B$0.08$0.14
DeepSeek V3SambaNova671B$0.06$0.12
LLaMA 3.3 70BSambaNova70B$0.06$0.12
QwQ 32BSambaNova32B$0.05$0.10
Qwen3 32BSambaNova32B$0.05$0.10
Nemotron 70BNVIDIA70B$0.06$0.12
LLaMA 3.3 70BNVIDIA70B$0.06$0.12
Mistral 7BNVIDIA7B$0.04$0.08
LLaMA 3.1 8BNVIDIA8B$0.04$0.08
Nemotron 3 Super 120BOpenRouter120B$0.08$0.14
Devstral 2 123BOpenRouter123B$0.08$0.14
Gemma 3 27BOpenRouter27B$0.08$0.14
LLaMA 3.3 70B FreeOpenRouter70B$0.08$0.14
Auto RouterOpenRouter$0.08$0.14
Step 3.5 FlashStepFun$0.07$0.30
GLM 4.5 AirZ.ai$0.07$0.30
budget

Budget Models

Upstream cost +10% markup — best value for everyday tasks

ModelProviderUpstream PriceIzzi Input / 1MIzzi Output / 1M
GPT-4o MiniOpenAI$0.15 / $0.60$0.165$0.660
GPT-4.1 MiniOpenAI$0.40 / $1.60$0.440$1.760
Gemini 2.5 Flash-LiteGoogle$0.13 / $0.75$0.143$0.825
Gemini 2.5 FlashGoogle$0.30 / $2.50$0.330$2.750
Grok 4.1 FastxAI$0.21 / $0.53$0.231$0.583
standard

Standard Models

Balanced performance and quality — includes approved flat-retail routes

ModelProviderUpstream PriceIzzi Input / 1MIzzi Output / 1M
GPT-5.6 LunaCodex LBFlat retail$0.045627$0.045627
Claude Haiku 4.5Claude$0.80 / $4.00$0.880$4.40
GPT-4.1OpenAI$2.00 / $8.00$2.20$8.80
GPT-5.1OpenAI$1.00 / $8.00$1.10$8.80
premium

Premium Models

Top-tier models — flat-retail SmartRouter routes are marked in the table

ModelProviderUpstream PriceIzzi Input / 1MIzzi Output / 1M
GPT-5.6 SolCodex LBFlat retail$0.064639$0.064639
GPT-5.6 TerraCodex LBFlat retail$0.045627$0.045627
Grok 4.5 High9RouterFlat retail$0.057034$0.057034
Claude Sonnet 4.6Claude$3.00 / $15.00$3.30$16.50
Claude Opus 4.6Claude$5.00 / $25.00$5.50$27.50
Claude Sonnet 4.5Claude$3.00 / $15.00$3.30$16.50
Claude Sonnet 4Claude$3.00 / $15.00$3.30$16.50
Claude Opus 4Claude$5.00 / $25.00$5.50$27.50
GPT-5.4OpenAI$2.50 / $15.00$2.75$16.50
GPT-5.2OpenAI$1.75 / $14.00$1.93$15.40
Grok 4xAI$3.00 / $15.00$3.30$16.50

Frequently Asked Questions

What is 1 Credit?

1 Credit = 1 USD = 26,300 VNĐ theo tỉ giá mặc định. Tài khoản mới nhận 5 credits miễn phí khi đăng ký.

Why are "free" models not free?

Izzi proxies free models through premium infrastructure (SambaNova, NVIDIA NIM, Cerebras, OpenRouter). The maintenance fee ($0.04–$0.08 / 1M tokens) covers server costs, monitoring, and reliability. This is 50–100× cheaper than paid models.

How is the +10% markup calculated?

Most paid models use upstream price × 1.10; rows marked Flat retail use the approved fixed SmartRouter rate. This supports API key management, rate limit optimization, failover routing, monitoring, and operational maintenance. Availability remains subject to upstream provider and infrastructure outages.

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?

Cache pricing is model-specific. GPT-5.6 and Grok 4.5 High use the same approved flat rate for input, output, and cached tokens. Other models may retain a discounted cache rate; see the current model row or API catalog.