廠商 · 2026-09-28
nan
| 模型 | 輸入 / 1M | 輸出 / 1M | 上下文 | 服務商 | 標籤 |
|---|---|---|---|---|---|
| MiMo-V2.6-Flash | 未公開 | 未公開 | 1.05M | 1 | tools · reasoning · vision · open-weights |
| Gemma 4 26B A4B IT衍生 | 未公開 | 未公開 | 262K | 1 | tools · json · reasoning · vision · open-weights |
| GLM-5.3衍生 | 未公開 | 未公開 | 1M | 1 | tools · json · reasoning · open-weights |
| GLM-5.3-Flash衍生 | 未公開 | 未公開 | 1M | 1 | tools · json · reasoning · vision · open-weights |
| Qwen-Image-2.1衍生 | 未公開 | 未公開 | 8K | 1 | open-weights |
| Qwen3.6 35B-A3B衍生 | 未公開 | 未公開 | 262K | 1 | tools · json · reasoning · vision · open-weights |
Frequently asked questions
How many AI models does nan offer?
We track 1 canonical nan models plus 5 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which nan model has the largest context window?
MiMo-V2.6-Flash leads at 1.05M tokens. This is the total of prompt + completion.
Which nan models support tool calling?
Multiple nan models support tool calling, with MiMo-V2.6-Flash being a popular pick. The capability column in the table above marks every model with nan tool-calling support.
Which nan models accept image input?
MiMo-V2.6-Flash accepts image input. Other vision-capable nan models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to nan?
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 nan 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.
Explore more
最近更新：
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.