Kimi K3.1 Pro HighSpeed
The high-speed K3.1 Pro variant for interactive coding and agent workflows.
Price comparison · USD / 1M tokens
Plan prices below assume full weekly allowance use over 30 days.
| Plan | Input | Output |
|---|---|---|
| Pay as you go | $3.333333Cached input $0.333333 | $13.333333 |
| Coding Plan Pro$29.90 / month | $0.4651 | |
| Coding Plan Max$49.90 / month | $0.2911 | |
| Coding Plan Pro Max$149 / month | $0.2483 | |
Connect this model
Coding Plan rate: 20 points / token
Use Kimi K3.1 Pro HighSpeed in a request
Set your base URL and key as described in the quickstart. Use the exact API model ID kimi-k3.1-pro-highspeed, even when the display name differs.
curl "$SIAPI_BASE_URL/v1/chat/completions" \
-H "Authorization: Bearer $SIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kimi-k3.1-pro-highspeed","messages":[{"role":"user","content":"Explain a binary search in one paragraph."}],"max_tokens":256}'Capabilities and configuration
| Display name | Kimi K3.1 Pro HighSpeed |
|---|---|
| API model ID | kimi-k3.1-pro-highspeed |
| Guide examples | Text, streaming and client-defined function tools |
| Reasoning choices | low, high, max |
| Image admission | Enabled in gateway configuration |
Low, High and Max. Thinking is always enabled; choose Low for less reasoning. The model default is Max.
Compare a concrete token workload
For 500,000 uncached input tokens, 500,000 cached input tokens and 1 million output tokens, Kimi K3.1 Pro HighSpeed costs $15.166666 with PAYG, or uses 40M points on a Coding Plan. Cached input is already part of the 1 million total input tokens.
The same workload on Kimi K3.1 Pro costs $7.666667 with PAYG, or uses 30M plan points. Compare the costs with your actual input/output mix, then evaluate results on your own task.
These are cost estimates from the published rates. Plan points count toward both allowance windows. See the Billing basics or estimate your workload.