Skip to main content
Providers

NanoGPT

Use nano-gpt/<model> with VoltAgent's model router.

Quick start​

import { Agent } from "@voltagent/core";

const agent = new Agent({
  name: "nano-gpt-agent",
  instructions: "You are a helpful assistant",
  model: "nano-gpt/deepseek/deepseek-r1",
});

Environment variables​

  • NANO_GPT_API_KEY

Provider package​

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL​

https://nano-gpt.com/api/v1

You can override the base URL by setting NANO_GPT_BASE_URL.

Provider docs​

Models​

Show models (21)
  • deepseek/deepseek-r1
  • deepseek/deepseek-v3.2:thinking
  • meta-llama/llama-3.3-70b-instruct
  • meta-llama/llama-4-maverick
  • minimax/minimax-m2.1
  • mistralai/devstral-2-123b-instruct-2512
  • mistralai/ministral-14b-instruct-2512
  • mistralai/mistral-large-3-675b-instruct-2512
  • moonshotai/kimi-k2-instruct
  • moonshotai/kimi-k2-thinking
  • nousresearch/hermes-4-405b:thinking
  • nvidia/llama-3_3-nemotron-super-49b-v1_5
  • openai/gpt-oss-120b
  • qwen/qwen3-235b-a22b-thinking-2507
  • qwen/qwen3-coder
  • z-ai/glm-4.6
  • z-ai/glm-4.6:thinking
  • zai-org/glm-4.5-air
  • zai-org/glm-4.5-air:thinking
  • zai-org/glm-4.7
  • zai-org/glm-4.7:thinking

Table of Contents