Yi Lightning
01ai/yi-lightningSpeed-first bilingual model: symmetric pricing and sub-second answers for interactive products.
Model overview
Context window
64K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
3
of 11 tags
Description
Yi Lightning is a language model from 01.AI. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. 01.AI’s stated focus is efficient bilingual frontier models. The weights are not published, so it is API-only.
Capabilities
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- JSON mode
- Constrains the response to valid JSON matching a schema you supply.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
Strengths & weaknesses
Strengths
- Fastest first token in the catalogue
- Symmetric in/out pricing
- Strong EN/ZH balance
Weaknesses
- 64K context only
- Depth trails larger models
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
This model is not provisioned yet; the rate is quoted on request.
Context window
64Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Not supported |
| Reasoning | Not supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
Chat interfaces
Autocomplete
Latency-critical features
Comparison
Compare against anything →| Attribute | Yi Lightning | Doubao 1.5 Pro | GPT-5.1 Mini |
|---|---|---|---|
| Context window | 64K | 256K | 400K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Supported | Supported |
| Vision input | Not supported | Not supported | Supported |
| Open weights | Not supported | Not supported | Not supported |
| Prompt caching | Not supported | Supported | Supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View 01.AI →01.AI · 零一万物 · Beijing, China · est. 2023
AI focused on extracting maximum capability per parameter, its Yi models punched far above their size class in bilingual benchmarks. The lab has since concentrated on the fast, inexpensive Yi-Lightning line for production workloads.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.
No. Yi Lightning is served through its provider's API only; the weights are not published, so self-hosting is not an option.
Prompt and response share one window: Yi Lightning accepts up to 64K tokens in total, so a long input leaves less room for the answer. The median across language models is 256K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
Doubao 1.5 Pro is the closest neighbour in the catalogue, with 256K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.