Inteligencia de modelos de IA

Proveedor · 2026-05-12

novita-ai

10 modelos canónicos18 entradas en total (incluidos derivados)
ModeloEntrada / 1MSalida / 1MContextoProveedoresEtiquetas
PaddleOCR-VL$0.020$0.02016K1vision · open-weights
Sao10k L3 8B Lunaris $0.050$0.0508K1json · open-weights
L3 8B Stheno V3.2$0.050$0.0508K1tools · open-weights
baichuan-m2-32b$0.070$0.070131K1open-weights
Mythomax L2 13B$0.090$0.0904K1open-weights
Ling-2.6-flash$0.100$0.300262K1tools · json · open-weights
XiaomiMiMo/MiMo-V2-Flash$0.100$0.300262K1tools · json · reasoning · open-weights
L31 70B Euryale V2.2$1.48$1.488K1tools · open-weights
L3 70B Euryale V2.1 $1.48$1.488K1tools · open-weights
Ling-2.6-1TDesconocidoDesconocido262K1tools · json · open-weights
deepseek/deepseek-ocr-2derivado$0.030$0.0308K1vision · open-weights
DeepSeek-OCRderivado$0.030$0.0308K1json · vision · open-weights
Qwen3 4Bderivado$0.030$0.030128K1reasoning · open-weights
DeepSeek R1 0528 Qwen3 8Bderivado$0.060$0.090128K1reasoning · open-weights
AutoGLM-Phone-9B-Multilingualderivado$0.035$0.13866K1vision · open-weights
DeepSeek V3 (Turbo) derivado$0.400$1.3064K1tools · open-weights
DeepSeek R1 (Turbo) derivado$0.700$2.5064K1tools · reasoning · open-weights
Deepseek Prover V2 671Bderivado$0.700$2.50160K1open-weights

Frequently asked questions

How many AI models does novita-ai offer?

We track 10 canonical novita-ai models plus 8 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which novita-ai model is the cheapest?

PaddleOCR-VL is currently the lowest-priced novita-ai model, at $0.020 per 1M input tokens and $0.020 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which novita-ai model has the largest context window?

Ling-2.6-flash leads at 262K tokens. This is the total of prompt + completion.

Which novita-ai models support tool calling?

Multiple novita-ai models support tool calling, with L3 8B Stheno V3.2 being a popular pick. The capability column in the table above marks every model with novita-ai tool-calling support.

Which novita-ai models accept image input?

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

What are the best alternatives to novita-ai?

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-ai 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.

Última actualización:

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.