# AZET AI API > OpenAI-compatible chat completions for open models and AZET's own models, operated by AZET LLC (Ohio, USA). Base URL https://api.azet.io/v1, auth header "Authorization: Bearer azk_...". Prepaid USD credit billed per token. ## Docs - [API reference](https://api.azet.io/docs): endpoints, parameters, billing, errors, limits - [OpenAPI spec](https://api.azet.io/openapi.json) - [Models and pricing](https://api.azet.io/models): every model with its own page, USD per 1M tokens, same as GET /v1/models - [Sitemap](https://api.azet.io/sitemap.xml) - [AZET Nunchi 1](https://api.azet.io/models/nunchi-1): AZET's Korean scam-message judge, model id azet/nunchi-1 - [Terms](https://api.azet.io/terms) · [Privacy](https://api.azet.io/privacy) · [Status](https://api.azet.io/status) ## Models - [deepseek-v4-flash-0731](https://api.azet.io/models/deepseek-v4-flash-0731): context 1048576 tokens, $0.3557 input / $1.0672 output per 1M tokens - [deepseek-v4-pro](https://api.azet.io/models/deepseek-v4-pro): context 1048576 tokens, $1.9404 input / $3.8808 output per 1M tokens - [deepseek-v4-pro-0813](https://api.azet.io/models/deepseek-v4-pro-0813): context 1048576 tokens, $1.0672 input / $3.2017 output per 1M tokens - [deepseek-v4.1-flash](https://api.azet.io/models/deepseek-v4.1-flash): context 1048576 tokens, $0.2425 input / $0.9702 output per 1M tokens - [deepseek-v4.1-flash-1017](https://api.azet.io/models/deepseek-v4.1-flash-1017): context 1048576 tokens, $0.2425 input / $0.9702 output per 1M tokens - [glm-5.1](https://api.azet.io/models/glm-5.1): context 200000 tokens, $1.1319 input / $3.5574 output per 1M tokens - [glm-5.2](https://api.azet.io/models/glm-5.2): context 200000 tokens, $1.1319 input / $3.5574 output per 1M tokens - [glm-5.3](https://api.azet.io/models/glm-5.3): context 200000 tokens, $1.1319 input / $3.5574 output per 1M tokens - [glm-5.3-prime](https://api.azet.io/models/glm-5.3-prime): context 200000 tokens, $2.2638 input / $7.1148 output per 1M tokens - [kimi-k2.7-code](https://api.azet.io/models/kimi-k2.7-code): context 262144 tokens, $0.7681 input / $3.234 output per 1M tokens - [kimi-k3](https://api.azet.io/models/kimi-k3): context 262144 tokens, $2.4255 input / $12.1275 output per 1M tokens - [qwen-flash](https://api.azet.io/models/qwen-flash): context 1000000 tokens, $0.0404 input / $0.3234 output per 1M tokens - [qwen-max](https://api.azet.io/models/qwen-max): context 32768 tokens, $1.2936 input / $5.1744 output per 1M tokens - [qwen-plus](https://api.azet.io/models/qwen-plus): context 1000000 tokens, $0.3234 input / $0.9702 output per 1M tokens - [qwen3-coder-flash](https://api.azet.io/models/qwen3-coder-flash): context 1000000 tokens, $0.2425 input / $1.2127 output per 1M tokens - [qwen3-vl-plus](https://api.azet.io/models/qwen3-vl-plus): context 262144 tokens, $0.1617 input / $1.2936 output per 1M tokens - [qwen3.5-flash](https://api.azet.io/models/qwen3.5-flash): context 1000000 tokens, $0.0809 input / $0.3234 output per 1M tokens - [qwen3.5-plus](https://api.azet.io/models/qwen3.5-plus): context 1000000 tokens, $0.3234 input / $1.9404 output per 1M tokens - [qwen3.6-flash](https://api.azet.io/models/qwen3.6-flash): context 1000000 tokens, $0.2021 input / $1.2127 output per 1M tokens - [qwen3.6-plus](https://api.azet.io/models/qwen3.6-plus): context 1000000 tokens, $0.4042 input / $2.4255 output per 1M tokens - [qwen3.7-flash](https://api.azet.io/models/qwen3.7-flash): context 1000000 tokens, $0.0243 input / $0.1051 output per 1M tokens - [qwen3.7-max](https://api.azet.io/models/qwen3.7-max): context 1000000 tokens, $2.0213 input / $6.0637 output per 1M tokens - [qwen3.7-plus](https://api.azet.io/models/qwen3.7-plus): context 1000000 tokens, $0.3234 input / $1.2936 output per 1M tokens - [qwen3.8-27b](https://api.azet.io/models/qwen3.8-27b): context 1000000 tokens, $0.4042 input / $2.4255 output per 1M tokens - [qwen3.8-flash](https://api.azet.io/models/qwen3.8-flash): context 1000000 tokens, $0.1213 input / $0.38 output per 1M tokens - [qwen3.8-max](https://api.azet.io/models/qwen3.8-max): context 1000000 tokens, $1.617 input / $4.851 output per 1M tokens - [azet/nunchi-1](https://api.azet.io/models/nunchi-1): context 15000 tokens, $0.1155 input / $0.1995 output per 1M tokens - [moonshotai/Kimi-K2.6](https://api.azet.io/models/moonshotai/Kimi-K2.6): context 262144 tokens, $0.4095 input / $1.89 output per 1M tokens - [moonshotai/Kimi-K2.7-Code](https://api.azet.io/models/moonshotai/Kimi-K2.7-Code): context 262144 tokens, $0.8736 input / $3.675 output per 1M tokens - [zai-org/GLM-5.2](https://api.azet.io/models/zai-org/GLM-5.2): context 1048576 tokens, $1.3125 input / $4.1475 output per 1M tokens - [zai-org/GLM-5.3](https://api.azet.io/models/zai-org/GLM-5.3): context 1048576 tokens, $1.2863 input / $4.0425 output per 1M tokens ## Image models - z-image-turbo: $0.0121 per image (maker's own price $0.015), POST /v1/images/generations {"model": "z-image-turbo", "prompt": "...", "size": "1024x1024"} returns a 24-hour image URL - qwen-image-2.0: $0.0283 per image (maker's own price $0.035), POST /v1/images/generations {"model": "qwen-image-2.0", "prompt": "...", "size": "1024x1024"} returns a 24-hour image URL - wan2.7-image: $0.0243 per image (maker's own price $0.03), POST /v1/images/generations {"model": "wan2.7-image", "prompt": "...", "size": "1024x1024"} returns a 24-hour image URL ## Coding tools - npx azet-ai claude | codex | opencode: runs that tool on your AZET key (POST /v1/messages for Claude Code, POST /v1/responses for Codex) - npx -y azet-ai mcp: MCP server (stdio) with tools models, chat, balance — add with: claude mcp add azet -- npx -y azet-ai mcp ## Endpoints - POST /v1/chat/completions — OpenAI Chat Completions shape, stream supported (final chunk carries usage) - POST /v1/images/generations — OpenAI Images shape, n = 1, returns data[0].url - GET /v1/models, GET /v1/models/{id} — models with pricing - GET /v1/balance, GET /v1/key, GET /v1/activity — credit, spend, 30-day activity