nafnaf.ai

Inference models

One API key. Compare models, context windows and token prices.

Prices are USD per million tokens. Free models do not use credits; paid models require an available balance. Start with the free Qwen API.

Qwen3.8 Flash-Next - Free

qwen3.8-flash-next

Free Qwen text generation through Chat Completions.

Input / 1M tokens
$0.00
Output / 1M tokens
$0.00
Cached input / 1M tokens
$0.00

Chat Completions · 262,144 token context

Get an API key

DeepSeek Flash - Free

deepseek-flash

Free DeepSeek V4.1 Flash text generation, reasoning, and tool calling.

Input / 1M tokens
$0.00
Output / 1M tokens
$0.00
Cached input / 1M tokens
$0.00

Responses / Chat Completions · 1,048,576 token context

Get an API key

MiMo v2.6 Flash

mimo-v2.6-flash

General-purpose text generation with thinking, tool calling, and structured outputs.

Input / 1M tokens
$0.20
Output / 1M tokens
$0.40
Cached input / 1M tokens
$0.003

Responses / Chat Completions · 1,048,576 token context

Get an API key

GLM 5.3 Flash Abliterated - Unavailable

glm-5.3-flash

A fast text model for reasoning, tool calling, and structured outputs.

Input / 1M tokens
$0.04
Output / 1M tokens
$0.50
Cached input / 1M tokens
$0.03

Responses / Chat Completions · 1,048,576 token context

This model is currently unavailable.

Use the API

Base URL: https://inference.nafnaf.ai/v1. Use the model ID above in your request. Available formats and limits vary by model.