ذكاء نماذج الذكاء الاصطناعي

مزود · 2026-05-22

routing-run

4 نموذج قياسي10 إجمالي السجلات (بما فيها المشتقة)
النموذجإدخال / 1Mإخراج / 1Mالسياقالمزودونالوسوم
Step 3.5 Flash$0.096$0.288262K1tools · reasoning · open-weights
Step 3.5 Flash 2603$0.100$0.300262K1tools · reasoning · open-weights
MiMo V2.5 Pro$0.450$1.351M1tools · reasoning · vision · open-weights
MiMo V2.5 Pro 6bit$0.450$1.351M1tools · reasoning · vision · open-weights
StepFun 3.5 Flashمشتق$0.096$0.288262K1tools · reasoning · open-weights
DeepSeek V4 Pro 6bitمشتق$0.493$0.7391M1tools · json · reasoning · open-weights
DeepSeek V4 Flash 6bitمشتق$0.493$0.7391M1tools · json · reasoning · open-weights
Mistral Large 3مشتق$0.500$1.50128K1tools · open-weights
Kimi K2.6 6bitمشتق$0.462$2.42262K1tools · json · reasoning · vision · open-weights
GLM 5.1 6bitمشتق$1.00$3.00203K1tools · json · reasoning

Frequently asked questions

How many AI models does routing-run offer?

We track 4 canonical routing-run models plus 6 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Which routing-run model is the cheapest?

Step 3.5 Flash is currently the lowest-priced routing-run model, at $0.096 per 1M input tokens and $0.288 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which routing-run model has the largest context window?

MiMo V2.5 Pro leads at 1M tokens. This is the total of prompt + completion.

Which routing-run models support tool calling?

Multiple routing-run models support tool calling, with Step 3.5 Flash being a popular pick. The capability column in the table above marks every model with routing-run tool-calling support.

Which routing-run models accept image input?

MiMo V2.5 Pro accepts image input. Other vision-capable routing-run models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to routing-run?

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 routing-run 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.