プロバイダー · 2026-05-12
siliconflow
| モデル | 入力 / 1M | 出力 / 1M | コンテキスト | プロバイダー | タグ |
|---|---|---|---|---|---|
| inclusionAI/Ling-mini-2.0 | $0.070 | $0.280 | 131K | 1 | tools · json |
| inclusionAI/Ring-flash-2.0 | $0.140 | $0.570 | 131K | 1 | tools · json · reasoning |
| inclusionAI/Ling-flash-2.0 | $0.140 | $0.570 | 131K | 1 | tools · json |
| tencent/Hunyuan-A13B-Instruct | $0.140 | $0.570 | 131K | 1 | tools · json |
| ByteDance-Seed/Seed-OSS-36B-Instruct | $0.210 | $0.570 | 262K | 1 | tools · json |
| tencent/Hunyuan-MT-7B | 不明 | 不明 | 33K | 1 | tools · json |
| deepseek-ai/deepseek-vl2派生 | $0.150 | $0.150 | 4K | 1 | tools · json · vision |
| Qwen/Qwen2.5-72B-Instruct-128K派生 | $0.590 | $0.590 | 131K | 1 | tools · json |
| Qwen/Qwen3-VL-32B-Thinking派生 | $0.200 | $1.50 | 262K | 1 | tools · json · reasoning · vision |
| Qwen/Qwen3-Omni-30B-A3B-Captioner派生 | $0.100 | $0.400 | 66K | 1 | tools · json |
Frequently asked questions
How many AI models does siliconflow offer?
We track 6 canonical siliconflow models plus 4 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.
Which siliconflow model is the cheapest?
inclusionAI/Ling-mini-2.0 is currently the lowest-priced siliconflow model, at $0.070 per 1M input tokens and $0.280 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which siliconflow model has the largest context window?
ByteDance-Seed/Seed-OSS-36B-Instruct leads at 262K tokens. This is the total of prompt + completion.
Which siliconflow models support tool calling?
Multiple siliconflow models support tool calling, with inclusionAI/Ling-mini-2.0 being a popular pick. The capability column in the table above marks every model with siliconflow tool-calling support.
What are the best alternatives to siliconflow?
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 siliconflow pricing data?
Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top siliconflow models
- inclusionAI/Ling-mini-2.0$0.07 in / $0.28 out
- inclusionAI/Ring-flash-2.0$0.14 in / $0.57 out
- inclusionAI/Ling-flash-2.0$0.14 in / $0.57 out
- tencent/Hunyuan-A13B-Instruct$0.14 in / $0.57 out
- ByteDance-Seed/Seed-OSS-36B-Instruct$0.21 in / $0.57 out
Browse by use case
Browse by capability
最終更新：
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.