AIモデルインテリジェンス

プロバイダー · 2026-11-15

stepping-stone

標準モデル 6 件全 6 件(派生 / ファインチューン含む)
モデル入力 / 1M出力 / 1Mコンテキストプロバイダータグ
MinerU2.5 2509 1.2B$0.024$0.07116K1vision · open-weights
LightOnOCR 2 1B$0.024$0.07116K1vision · open-weights
BGE M3$0.119Unknown8K1open-weights
BGE Reranker V2 M3$0.119Unknown8K1open-weights
Apertus v1.5 8B$0.024$0.119131K1tools · reasoning · vision · open-weights
olmOCR 2 7B$0.071$0.3458K1vision · open-weights

Frequently asked questions

How many AI models does stepping-stone offer?

We track 6 canonical stepping-stone models. The list is recomputed daily.

Which stepping-stone model is the cheapest?

MinerU2.5 2509 1.2B is currently the lowest-priced stepping-stone model, at $0.024 per 1M input tokens and $0.071 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which stepping-stone model has the largest context window?

Apertus v1.5 8B leads at 131K tokens. This is the total of prompt + completion.

Which stepping-stone models support tool calling?

Multiple stepping-stone models support tool calling, with Apertus v1.5 8B being a popular pick. The capability column in the table above marks every model with stepping-stone tool-calling support.

Which stepping-stone models accept image input?

MinerU2.5 2509 1.2B accepts image input. Other vision-capable stepping-stone models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to stepping-stone?

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 stepping-stone 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.

最終更新:

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.