AI 모델 인텔리전스

제공자 · 2026-05-12

novita

표준 모델 11개총 11개 (파생/파인튜닝 포함)
모델입력 / 1M출력 / 1M컨텍스트제공자태그
DeepSeek-V3.2$0.270$0.400128K1tools · reasoning · open-weights
Kimi-K2.5$0.600$3.00128K1tools · reasoning · vision
GLM-5$1.00$3.20205K1tools · reasoning
Kimi-K2.6$0.960$4.04262K1tools · reasoning · vision · open-weights
GLM-4.6미공개미공개Unknown1tools
glm-4.6v미공개미공개131K1tools · reasoning · vision
glm-4.7미공개미공개205K1tools · reasoning
glm-4.7-flash미공개미공개200K1tools · reasoning
glm-4.7-n미공개미공개205K1tools · reasoning
kimi-k2-thinking미공개미공개256K1tools · reasoning
minimax-m2.1미공개미공개205K1tools · reasoning

Frequently asked questions

How many AI models does novita offer?

We track 11 canonical novita models. The list is recomputed daily from models.dev.

Which novita model is the cheapest?

DeepSeek-V3.2 is currently the lowest-priced novita model, at $0.270 per 1M input tokens and $0.400 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which novita model has the largest context window?

Kimi-K2.6 leads at 262K tokens. This is the total of prompt + completion.

Which novita models support tool calling?

Multiple novita models support tool calling, with DeepSeek-V3.2 being a popular pick. The capability column in the table above marks every model with novita tool-calling support.

Which novita models accept image input?

Kimi-K2.5 accepts image input. Other vision-capable novita models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to novita?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this novita pricing data?

Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

마지막 업데이트:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.