ذكاء نماذج الذكاء الاصطناعي

مزود · 2026-06-11

fastrouter

5 نموذج قياسي12 إجمالي السجلات (بما فيها المشتقة)
النموذجإدخال / 1Mإخراج / 1Mالسياقالمزودونالوسوم
Sarvam 30B$0.020$0.100128K1tools · reasoning · open-weights
Sarvam 105B$0.040$0.160131K1tools · reasoning · open-weights
Lucid Originغير معروفغير معروف4K1vision
Lucid Realismغير معروفغير معروف4K1vision
Wan 2.6غير معروفغير معروف400K1vision · open-weights
GPT Realtime 1.5مشتق$4.00$16.0032K1tools · vision
Imagen 4 Fastمشتقغير معروفغير معروف4801
Imagen 4 Ultraمشتقغير معروفغير معروف4801
Seedance 2مشتقغير معروفغير معروف4K1vision
Veo 3.1مشتقغير معروفغير معروف400K1vision
Veo 3.1 Fastمشتقغير معروفغير معروف400K1vision
Veo 3.1 Liteمشتقغير معروفغير معروف400K1vision

Frequently asked questions

How many AI models does fastrouter offer?

We track 5 canonical fastrouter models plus 7 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Which fastrouter model is the cheapest?

Sarvam 30B is currently the lowest-priced fastrouter model, at $0.020 per 1M input tokens and $0.100 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which fastrouter model has the largest context window?

Wan 2.6 leads at 400K tokens. This is the total of prompt + completion.

Which fastrouter models support tool calling?

Multiple fastrouter models support tool calling, with Sarvam 30B being a popular pick. The capability column in the table above marks every model with fastrouter tool-calling support.

Which fastrouter models accept image input?

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

What are the best alternatives to fastrouter?

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 fastrouter 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.

آخر تحديث:

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.