Inteligência em modelos de IA

Provedor · 2026-05-12

azure-cognitive-services

9 modelos canônicos12 entradas no total (incluindo derivados)
ModeloEntrada / 1MSaída / 1MContextoProvedoresEtiquetas
text-embedding-3-small$0.020Unknown8K1
Ministral 3B$0.040$0.040128K1tools · open-weights
text-embedding-ada-002$0.100Unknown8K1
text-embedding-3-large$0.130Unknown8K1
Model Router$0.140Unknown128K1tools · vision
o4-mini$1.10$4.40200K1tools · reasoning · vision
MAI-DS-R1$1.35$5.40128K1reasoning
Codex Mini$1.50$6.00200K1tools · reasoning
o1$15.00$60.00200K1tools · reasoning · vision
Embed v3 Englishderivado$0.100Unknown5121open-weights
Embed v3 Multilingualderivado$0.100Unknown5121open-weights
Embed v4derivado$0.120Unknown128K1vision · open-weights

Frequently asked questions

How many AI models does azure-cognitive-services offer?

We track 9 canonical azure-cognitive-services models plus 3 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which azure-cognitive-services model is the cheapest?

text-embedding-3-small is currently the lowest-priced azure-cognitive-services 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 azure-cognitive-services model has the largest context window?

o4-mini leads at 200K tokens. This is the total of prompt + completion.

Which azure-cognitive-services models support tool calling?

Multiple azure-cognitive-services models support tool calling, with Ministral 3B being a popular pick. The capability column in the table above marks every model with azure-cognitive-services tool-calling support.

Which azure-cognitive-services models accept image input?

Model Router accepts image input. Other vision-capable azure-cognitive-services models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to azure-cognitive-services?

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 azure-cognitive-services 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.