Models - NinjaChat Developers

Not sure which model to pick? Set model: "auto" and NinjaChat picks the best one for your prompt. Learn more about smart routing

Pick a model

Chat prices below are a typical price — a derived reference at 5K input / 1K output tokens, not a flat fee. Chat bills per token; see Pricing for the live rates.

I want to…	Model	Typical price	ID
Let NinjaChat decide	Auto (Balanced)	resolved model’s rate	`auto`
Build a production chatbot	GPT-5	~$0.0255	`gpt-5`
Generate high-quality code	Claude Sonnet 4.6	~$0.0336	`claude-sonnet-4.6`
Do math and logical reasoning	o3-mini	~$0.0112	`o3-mini`
Get the best possible answer	Claude Opus 4.6	~$0.056	`claude-opus-4.6`
Classify or extract text (budget)	DeepSeek V3	~$0.0064	`deepseek-v3`
Fast real-time chat	Gemini 3 Flash	~$0.0066	`gemini-3-flash`
Analyze long documents	Gemini 2.5 Pro	~$0.0182	`gemini-2.5-pro`
Generate images	Nano Banana 2	$0.06/img	`nano-banana-2`
Generate video	Veo 3.1 Fast	$3.00/video	`veo-3.1-fast`
Search the web	Web Search	$0.05/query	—

Browse all models with full specs, context windows, and pricing in the Models tab.

Fetch models via API

GET https://www.ninjachat.ai/api/v1/models

Returns metadata per model: capabilities, context_window, max_output_tokens, speed, and recommended_for. Supports filtering by tier, capability, and virtual.