novai-python
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NOVAI_API_KEY | Yes | Your NovAI API key (e.g. sk-...). Obtain one at https://aiapi-pro.com/register ($2 free credit). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| novai_list_modelsA | List every model id available on the NovAI gateway (111 models). Use when the user asks which models exist. For zero-cost models use novai_free_models; for prices use novai_cheapest or novai_pricing_feed. Returns a sorted list of model id strings (no prices). |
| novai_chatA | Send a chat completion to a Chinese LLM (DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao...). Args: model: model id from novai_list_models (e.g. deepseek-v4-flash). prompt: user message. system: optional system prompt. Returns the assistant reply as text. Requires NOVAI_API_KEY. For image generation use novai_generate_image instead. |
| novai_generate_imageA | Generate images with a Chinese image model (Seedream, Hunyuan Image, CogView, Wan...). Args: model: image model id (e.g. doubao-seedream-5.0, cogview-3-flash). prompt: image description. Returns a list of generated image URLs. Billed per image: check novai_pricing_feed for the per-image price before calling. For chat use novai_chat instead. |
| novai_free_modelsA | List the 5 models that are free to call on NovAI (GLM Flash family: text, vision, image, video). Use when the user wants zero-cost calls. These models are charged $0 but have a free-tier rate limit (10 free-model calls/day, 5 requests/min). For the full paid+free catalogue use novai_list_models. Returns a list of model ids. |
| novai_cheapestA | Return the cheapest model in one category from the live price leaderboard. Args: category: one of "Chat / LLM", "Image", "Video", "3D", "Audio", "Embedding" (default "Chat / LLM"). Returns a single model record with name, price_usd, unit and url. Use novai_pricing_feed when you need the full ranked feed across all categories. |
| novai_pricing_feedA | Return the complete live price leaderboard (all categories, models ranked by normalized cost). Use for comparisons or cost tables. For one quick answer use novai_cheapest instead. Returns {generated_at, categories: [{category, models: [{name, price_usd, unit, url}]}]}. Units differ (per 1M tokens / per generation / per image / flat) - always compare by unit. |
| novai_transparencyA | Return NovAI's published platform metrics: 0% platform fee, 1.0x price multiplier, refund policy, rate limits and billed units. Use when the user asks how billing or pricing policy works. For actual model prices use novai_pricing_feed. Returns a JSON object. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a distinct purpose, and the descriptions explicitly resolve the near-overlaps: novai_list_models vs novai_free_models, and novai_cheapest vs novai_pricing_feed each point to the other with clear 'use X instead' guidance. Chat and image generation are cleanly separated by modality.
All tools share the novai_ prefix and snake_case, which is highly predictable. Minor deviation: some names are verb-led (novai_chat, novai_list_models, novai_generate_image) while others are noun-led (novai_free_models, novai_cheapest, novai_pricing_feed, novai_transparency), but each is still self-explanatory.
Seven tools is well within the ideal range and each one earns its place: model discovery, chat, image generation, and three distinct pricing/policy views. No redundancy or filler.
Core workflows (discover models, chat, generate images, check pricing/policy) are covered, but the pricing tool exposes Video, 3D, Audio, and Embedding categories with no corresponding callable tools, and there is no multi-turn/conversation-state or token-accounting support. These are notable gaps an agent would hit when users ask for non-chat modalities.