GET
/v1/schemas/replicate/chat/models/moonshotai/kimi-k2.6/predictions
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace3080170e895a1af13bff906144ecb68900e1e3f034ed7353e3d7dc2f8448b91b{
"fetchedAt": 1791350061,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
4 properties · 1 required · 2 $defs| property | type | description | constraints |
|---|---|---|---|
| input* | Input | ||
| stream | boolean | **This field is deprecated.** | |
| webhook | string | An HTTPS URL for receiving a webhook when the prediction has new output. The webhook will be a POST request where the request body is the same as the response body of the [get prediction](#predictions.get) operation. If there are network problems, we will retr… | |
| webhook_events_filter | enum[] | By default, we will send requests to your webhook URL whenever there are new outputs or the prediction has finished. You can change which events trigger webhook requests by specifying `webhook_events_filter` in the prediction request: |
Types
2 $defsInputobject
| top_p | number | Nucleus sampling probability threshold. | 0 ≤ n ≤ 1 · default: 1 |
| prompt | string | Text prompt to send to Kimi K2.6. | default: "" |
| max_tokens | integer | Maximum number of tokens to generate. | 1 ≤ n ≤ 32768 · default: 2048 |
| image_input | string[] | Optional list of images to include in the prompt. Kimi K2.6 supports vision inputs. | default: [] |
| temperature | number | Sampling temperature. Higher values make output more random. | 0 ≤ n ≤ 2 · default: 0.6 |
| system_prompt | string | System prompt to guide the model's behavior. | default: "You are a helpful assistant." |
| presence_penalty | number | Penalizes new tokens based on whether they appear in the text so far. | -2 ≤ n ≤ 2 · default: 0 |
| reasoning_effort | enum | An enumeration. | none | low | medium | high |
| frequency_penalty | number | Penalizes new tokens based on their existing frequency in the text so far. | -2 ≤ n ≤ 2 · default: 0 |
reasoning_effortenum
An enumeration.
none | low | medium | high
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"replicate","endpointId":"models/moonshotai/kimi-k2.6/predictions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}