AI 모델 인텔리전스

제공자 · 2026-06-29

jiekou

표준 모델 2개총 6개 (파생/파인튜닝 포함)
모델입력 / 1M출력 / 1M컨텍스트제공자태그
o4-mini$1.10$4.40200K1tools · json · vision
XiaomiMiMo/MiMo-V2-Flash미공개미공개262K1tools · json · reasoning · open-weights
gemini-2.5-flash-lite-preview-06-17파생$0.090$0.3601.05M1tools · json · reasoning · vision
gemini-2.5-flash-preview-05-20파생$0.135$3.151.05M1tools · json · reasoning · vision
gemini-2.5-pro-preview-06-05파생$1.13$9.001.05M1tools · json · reasoning · vision
grok-4-0709파생$2.70$13.50256K1tools · json · vision

Frequently asked questions

How many AI models does jiekou offer?

We track 2 canonical jiekou models plus 4 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Which jiekou model is the cheapest?

o4-mini is currently the lowest-priced jiekou model, at $1.10 per 1M input tokens and $4.40 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which jiekou model has the largest context window?

XiaomiMiMo/MiMo-V2-Flash leads at 262K tokens. This is the total of prompt + completion.

Which jiekou models support tool calling?

Multiple jiekou models support tool calling, with o4-mini being a popular pick. The capability column in the table above marks every model with jiekou tool-calling support.

Which jiekou models accept image input?

o4-mini accepts image input. Other vision-capable jiekou models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to jiekou?

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 jiekou pricing data?

Daily. Our pipeline syncs every 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.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.