ERNIE 4.5
baidu/ernie-4.5Baidu's open multimodal flagship, deep Chinese knowledge grounding with vision input included.
Model overview
Context window
128K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
4
of 11 tags
Description
ERNIE 4.5 is a language model from Baidu ERNIE. 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. Baidu ERNIE’s stated focus is china's longest-running LLM lineage. 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.
- Vision input
- Accepts images alongside text in the prompt.
Strengths & weaknesses
Strengths
- Strong knowledge grounding
- Vision input standard
- Long lineage of iteration
Weaknesses
- Coding trails specialists
- Smaller context than peers
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
128Ktokens
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 | 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
Knowledge products
Search augmentation
Chinese-market assistants
Comparison
Compare against anything →| Attribute | ERNIE 4.5 | ERNIE X1 | Hunyuan Large |
|---|---|---|---|
| Context window | 128K | 128K | 256K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Not supported | Supported |
| Vision input | Supported | Not supported | Not supported |
| Open weights | Not supported | Not supported | Supported |
| Prompt caching | Not supported | Not supported | Not supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View Baidu ERNIE →Baidu ERNIE · 文心一言 · Beijing, China · est. 2019 (ERNIE line; parent Baidu founded 2000)
ERNIE predates the modern LLM wave. Baidu has iterated the line since 2019, giving it the longest continuous model lineage in China.
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. ERNIE 4.5 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: ERNIE 4.5 accepts up to 128K 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.
ERNIE X1 is the closest neighbour in the catalogue, with 128K 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.