Inteligência em modelos de IA

Provedor · 2026-05-12

vercel

12 modelos canônicos58 entradas no total (incluindo derivados)
ModeloEntrada / 1MSaída / 1MContextoProvedoresEtiquetas
Titan Text Embeddings V2$0.020Unknown8K1
Nova Micro$0.035$0.140128K1tools
Trinity Mini$0.050$0.150131K1
Nova Lite$0.060$0.240300K1tools · vision
Trinity Large Thinking$0.250$0.900262K1tools · reasoning · open-weights
Trinity Large Preview$0.250$1.00131K1tools
INTELLECT 3$0.200$1.10131K1tools · reasoning
Nova 2 Lite$0.300$2.501M1reasoning · vision
Nova Pro$0.800$3.20300K1tools · vision
Interfaze Beta$1.50$3.501M1reasoning
v0-1.5-md$3.00$15.00128K1tools · reasoning · vision
v0-1.0-md$3.00$15.00128K1tools · reasoning · vision
Text Embedding 005derivado$0.030Unknown8K1
Text Multilingual Embedding 002derivado$0.030Unknown8K1
Ministral 3B (latest)derivado$0.040$0.040128K1tools · open-weights
Embed v4.0derivado$0.120Unknown8K1
Codestral Embedderivado$0.150Unknown8K1
Ministral 8B (latest)derivado$0.100$0.100128K1tools · open-weights
Qwen3-14Bderivado$0.060$0.24041K1tools · reasoning
Qwen3-30B-A3Bderivado$0.080$0.29041K1tools · reasoning
Qwen 3.32Bderivado$0.100$0.30041K1tools · reasoning
Ministral 14Bderivado$0.200$0.200256K1vision
Devstral Small 1.1derivado$0.100$0.300128K1tools
Qwen3 235B A22B Instruct 2507derivado$0.130$0.60041K1tools
Mistral Small (latest)derivado$0.150$0.600256K1tools · reasoning · vision · open-weights
Nvidia Nemotron Nano 12B V2 VLderivado$0.200$0.600131K1tools · reasoning · vision
Codestral (latest)derivado$0.300$0.900256K1tools · open-weights
Mistral Large 3derivado$0.500$1.50256K1vision
Seed 1.6derivado$0.250$2.00256K1tools · reasoning
Seed 1.8derivado$0.250$2.00256K1tools · reasoning · vision
Mistral Medium 3.1derivado$0.400$2.00128K1tools · vision
MiniMax M2.1 Lightningderivado$0.300$2.40205K1tools · reasoning
Qwen3 235B A22B Thinking 2507derivado$0.300$2.90262K1tools · reasoning · vision
Qwen3 VL Instructderivado$0.700$2.80131K1tools · vision · open-weights
Sonar Reasoningderivado$1.00$5.00127K1reasoning
Magistral Medium (latest)derivado$2.00$5.00128K1tools · reasoning · open-weights
Qwen 3 Max Thinkingderivado$1.20$6.00256K1tools · reasoning · open-weights
Codex Miniderivado$1.50$6.00200K1tools · reasoning · vision
Grok 4.20 Non-Reasoningderivado$2.00$6.002M1tools · vision
Grok 4.20 Beta Non-Reasoningderivado$2.00$6.002M1tools · vision
Grok 4.20 Reasoningderivado$2.00$6.002M1tools · reasoning · vision
Grok 4.20 Multi Agent Betaderivado$2.00$6.002M1tools · reasoning
Grok 4.20 Beta Reasoningderivado$2.00$6.002M1tools · reasoning · vision
Pixtral Large (latest)derivado$2.00$6.00128K1tools · vision · open-weights
Qwen 3.6 Max Previewderivado$1.30$7.80240K1tools · reasoning · vision · open-weights
Qwen3 VL Thinkingderivado$0.700$8.40131K1tools · reasoning · vision · open-weights
GPT 5.1 Thinkingderivado$1.25$10.00400K1tools · reasoning · vision
GPT-5.1 Instantderivado$1.25$10.00128K1tools · reasoning · vision
Kimi K2 Turboderivado$2.40$10.00256K1tools
Nano Banana Pro (Gemini 3 Pro Image)derivado$2.00$120.0066K1
Devstral 2derivadoDesconhecidoDesconhecido256K1tools
Devstral Small 2derivadoDesconhecidoDesconhecido256K1tools
Gemini Embedding 2derivadoDesconhecidoDesconhecidoUnknown1
Grok Imagine ImagederivadoDesconhecidoDesconhecidoUnknown1
Grok Imagine Image ProderivadoDesconhecidoDesconhecidoUnknown1
Imagen 4derivadoDesconhecidoDesconhecido4801
Imagen 4 FastderivadoDesconhecidoDesconhecido4801
Imagen 4 UltraderivadoDesconhecidoDesconhecido4801

Frequently asked questions

How many AI models does vercel offer?

We track 12 canonical vercel models plus 46 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which vercel model is the cheapest?

Titan Text Embeddings V2 is currently the lowest-priced vercel model, at $0.020 per 1M input tokens and Unknown per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which vercel model has the largest context window?

Nova 2 Lite leads at 1M tokens. This is the total of prompt + completion.

Which vercel models support tool calling?

Multiple vercel models support tool calling, with Nova Micro being a popular pick. The capability column in the table above marks every model with vercel tool-calling support.

Which vercel models accept image input?

Nova Lite accepts image input. Other vision-capable vercel models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to vercel?

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 vercel 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 atualização:

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.