Skip to main content
Enabled when NOVITA_API_KEY is set in your environment.

​
Overview

The @standardagents/novita package provides a Novita AI provider factory for Standard Agents. It targets Novita’s OpenAI-compatible Chat Completions API and adds typed providerOptions, authenticated model discovery, request inspection, tool calling, streaming, structured outputs, and live catalog pricing.

Key Features

  • Direct integration with https://api.novita.ai/openai/v1/chat/completions
  • Live model discovery from https://api.novita.ai/openai/v1/models
  • Tool calling, structured outputs, streaming, and reasoning controls
  • Catalog price normalization into inputPrice, outputPrice, cachedPrice, and usage.pricing

​
Installation

npm
npm install @standardagents/novita
pnpm
pnpm add @standardagents/novita
yarn
yarn add @standardagents/novita

​
Quick Start

agents/models/novita_reasoning.ts
import { defineModel } from '@standardagents/spec';
import { novita } from '@standardagents/novita';

export default defineModel({
  name: 'novita-reasoning',
  provider: novita,
  model: 'deepseek/deepseek-v3.2',
});

​
Provider Options

import { defineModel } from '@standardagents/spec';
import { novita } from '@standardagents/novita';

export default defineModel({
  name: 'novita-agentic',
  provider: novita,
  model: 'zai-org/glm-5.2',
  providerOptions: {
    seed: 42,
    top_k: 40,
    separate_reasoning: true,
    enable_thinking: true,
  },
});

​
Available Options

OptionTypeDescription
seednumberBest-effort deterministic sampling seed
frequency_penaltynumberPenalize repeated tokens based on frequency
presence_penaltynumberPenalize repeated tokens based on presence
repetition_penaltynumberNovita repetition penalty
top_knumberTop-k sampling limit
min_pnumberMinimum probability threshold relative to the most likely token
logit_biasRecord<string, number>Token logit biases
logprobsbooleanReturn output token log probabilities
top_logprobsnumberNumber of top logprobs to return
separate_reasoningbooleanRequest reasoning content separately when supported
enable_thinkingbooleanEnable or disable model thinking when supported
modalitiesstring[]Output modalities for models that can return audio
The schema is passthrough, so newly documented Novita fields can be supplied before this package adds first-class typings.

​
Model IDs

Novita model IDs are sent directly, for example:
  • zai-org/glm-5.2
  • moonshotai/kimi-k2.7-code
  • minimax/minimax-m3
  • deepseek/deepseek-v4-pro
  • deepseek/deepseek-v4-flash
  • deepseek/deepseek-v3.2
The provider reads authenticated model metadata from https://api.novita.ai/openai/v1/models and exposes those models in the Standard Agents UI. Novita reports catalog prices as scaled integers. The provider normalizes those values to USD per 1M tokens before returning inputPrice, outputPrice, cachedPrice, and per-request usage.pricing. When Novita includes pricing.input_cache_read.price_per_m, the provider maps it to usage.pricing.cachedInputPerMillion and uses it for prompt_tokens_details.cached_tokens. Cache write tokens remain normal prompt input tokens and are priced at the standard input rate. Custom or private Novita models should still set inputPrice, outputPrice, and cachedPrice explicitly if they do not appear in Novita’s model catalog.

​
Environment Setup

.dev.vars
NOVITA_API_KEY=...
For Cloudflare Workers: 
wrangler secret put NOVITA_API_KEY

​
Notes

  • The provider uses Chat Completions, not OpenAI Responses.
  • Novita’s model catalog requires authentication.
  • reasoning.level automatically enables separate_reasoning and enable_thinking; set provider options directly when you need model-specific control.
  • For custom base URLs, configure the provider baseUrl slot with the full OpenAI-compatible base, such as https://api.novita.ai/openai/v1.

Models

Core model concepts

Cerebras Provider

Compare another Chat Completions provider

OpenRouter Provider

Compare with a multi-provider gateway