OpenAI
Anthropic
DeepSeek
Grok
Kimi
MiMo / GLM
Zhipu AI
xAIChoose your model
Compare multiple model families in one catalog and select an option that suits your application.
A WORLD OF MODELS. ONE CONNECTION.
The right model. One simple API.
Explore leading AI model families, compare token prices, and get API access with a conversation on Telegram.
32Models
7Model families
$0.04Rates from / 1M
OpenAI
Anthropic
DeepSeek
Zhipu AI
xAI
MiMo
Kimi
WHY ZADMODEL
More possibilities. Less complexity.
ZadModel brings your model options together. Find an option for your project, understand the price, and talk directly with our team to get started.
Understand your costs
See input, output, and cache prices separately, down to the smallest listed rate.
Talk to a real person
Discuss availability, credit, payment, and setup directly with our team on Telegram.
THE MODEL CATALOG
Models, priced clearly.
Compare input, output, and cached-input rates. Every price below is in USD per one million tokens.
32 models shownUSD / 1M tokens
| Model | Input | Output | Cache | Order on Telegram |
|---|---|---|---|---|
GPT-6 AstraOpenAI | $0.90 | $0.90 | $0.08 | Order |
GPT-6.1 SolOpenAI | $0.20 | $0.20 | $0.04 | Order |
GPT-6 SolOpenAI | $0.40 | $0.40 | $0.08 | Order |
GPT-6 LunaOpenAI | $0.10 | $0.10 | $0.02 | Order |
GPT-5.6 SolOpenAI | $0.90 | $0.90 | $0.08 | Order |
GPT-5.6 TerraOpenAI | $0.90 | $0.90 | $0.08 | Order |
GPT-5.6 LunaOpenAI | $0.90 | $0.90 | $0.08 | Order |
GPT-5.5OpenAI | $0.90 | $0.90 | $0.08 | Order |
Claude Fable 5Anthropic | $0.90 | $0.90 | $0.08 | Order |
Claude Sonnet 5Anthropic | $0.90 | $0.90 | $0.08 | Order |
Claude Sonnet 5.5Anthropic | $1.00 | $1.00 | $0.12 | Order |
Claude Opus 4.6Anthropic | $0.90 | $0.90 | $0.08 | Order |
Claude Opus 4.7Anthropic | $0.90 | $0.90 | $0.08 | Order |
Claude Opus 4.8Anthropic | $0.90 | $0.90 | $0.08 | Order |
Claude Opus 5Anthropic | $0.90 | $0.90 | $0.08 | Order |
Claude Opus 5.5Anthropic | $1.60 | $1.60 | $0.16 | Order |
DeepSeek V4.1 FlashDeepSeek | $0.04 | $0.04 | $0.01 | Order |
DeepSeek V4 Flash (0731)DeepSeek | $0.06 | $0.06 | $0.0054 | Order |
DeepSeek V4 ProDeepSeek | $0.50 | $0.50 | $0.10 | Order |
DeepSeek V4 Pro (Uncensored)DeepSeek | $0.50 | $0.50 | $0.10 | Order |
GLM 5.2Zhipu AI | $0.30 | $0.30 | $0.10 | Order |
GLM 5.3Zhipu AI | $0.20 | $0.20 | $0.06 | Order |
GLM 5.3 (Uncensored)Zhipu AI | $0.20 | $0.20 | $0.06 | Order |
GLM 5.3 FlashZhipu AI | $0.10 | $0.10 | $0.0088 | Order |
GLM 5.3 Flash (Uncensored)Zhipu AI | $0.10 | $0.10 | $0.0088 | Order |
GLM 5.3 Flash AbliteratedZhipu AI | $0.40 | $0.40 | $0.10 | Order |
Grok 4.7xAI | $0.20 | $0.20 | $0.04 | Order |
Grok 4.6xAI | $0.20 | $0.20 | $0.04 | Order |
Grok 4.5xAI | $0.20 | $0.20 | $0.04 | Order |
MiMo V2.6 ProMiMo | $0.40 | $0.40 | $0.08 | Order |
MiMo V2.6 FlashMiMo | $0.20 | $0.20 | $0.04 | Order |
Kimi K3Kimi | $0.30 | $0.30 | $0.06 | Order |
No models found. Try another name or family.
Input and output are billed separately at their listed rates. Cache pricing applies to eligible cached-input tokens. Availability, reasoning support, and context limits depend on the selected model; confirm details when ordering.
Prices last updated:GETTING STARTED
From a model to your next idea.
A straightforward conversation is all it takes to begin.
Find your model
Browse the catalog and compare the rates for your intended usage.
Message us on Telegram
Send the model name and the credit amount you would like to purchase.
Get connected
Confirm payment and setup with our team, then receive your API access details.
GOOD TO KNOW
A little clarity before you start.
What does “per one million tokens” mean?
Tokens are units of text processed by a model. Your input and the generated output are counted separately and billed at their respective rates.
How does cache pricing work?
The cache rate applies when the selected model and provider recognize eligible cached-input tokens. New input uses the input rate.
How do I order API access?
Choose a model and message @ZadModel on Telegram. We will confirm availability, credit, payment, and your connection details.
Do all models support reasoning and the same context length?
Capabilities and context limits vary by model and provider. Ask us to confirm the requirements of your application before ordering.
Let’s build something.
Found your model? Talk to us about access and your next project.