Moonshot route
kimi-k3.1-pro-highspeed
Kimi K3.1 Pro Highspeed API access.
The same Kimi K3.1 Pro model served at 2-3x the output speed, released 23 October 2026. $4 / $20 per 1M tokens, double K3.1 Pro. Cache reads are $0.32 per 1M. Reasoning is always on, with effort low / high / max. See the Kimi K3.1 Pro API pricing notes.
Input / 1M tokens
$4.00
Output / 1M tokens
$20.00
Cached input / 1M tokens
$0.32
Context window
1M
Provider
Moonshot
Workload calculator
Put the token rate into context.
These examples apply the published input and output rates directly. Actual cost follows the exact tokens your client sends and the model returns.
This route is the 60th cheapest of 69 comparable text models and cheaper than 8 on the same key. Its context window ranks 14th of 69.
Short request
$0.060
10K input + 1K output
Agent turn
$0.60
100K input + 10K output
Exact token billing
No request minimum
One model ID change
OpenAI compatible
Cost neighbourhood
Nearby routes, same workload.
Every comparison uses the same 100K-input / 10K-output turn. Changing route is a one-line model ID edit.
Price does not measure task quality. For generation routes, see GPT Image 2.
First request
Route it in one call.
Use any OpenAI SDK or tool. Keep the request shape, point the base URL at RouterPlex, and set the model ID shown here.
Read the quickstartcurl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "kimi-k3.1-pro-highspeed","messages": [{"role": "user", "content": "Hello!"}]}'
Route notes
Questions before production traffic.
01How much does the Kimi K3.1 Pro Highspeed API cost?+
Through RouterPlex, Kimi K3.1 Pro Highspeed costs $4.00 per 1M input tokens and $20.00 per 1M output tokens — the vendor list price with 0% markup, billed per token from a prepaid balance you top up from $5. Cached input tokens are billed at $0.32 per 1M instead of the full input rate, which is most of the prompt on a repeated agent or coding loop. RouterPlex bills $4 input / $20 output per 1M tokens, Moonshot's list price. Cached prompt tokens are billed at $0.32 per 1M, not Moonshot's published $0.20 cache-hit rate: our cache price is set from what our upstream charges us for a cached token, so it does not follow the lab's rate.
02What does one Kimi K3.1 Pro Highspeed agent turn cost?+
A 100K-token input with a 10K-token reply costs about $0.60 on Kimi K3.1 Pro Highspeed. That makes it the 60th cheapest of 69 comparable text models on RouterPlex, roughly 50.0× the cost of the cheapest option (Muse Spark 1.2 Contributor).
03What is a cheaper alternative to Kimi K3.1 Pro Highspeed?+
GLM-5.3 Abliterated from Zhipu is the closest cheaper model on RouterPlex — $0.46 per agent turn against $0.60 for Kimi K3.1 Pro Highspeed, at $4.00/1M input and $6.00/1M output. Both run on the same key and the same endpoint, so switching is a one-line model ID change.
04Is Kimi K3.1 Pro Highspeed cheaper than Claude Opus 4.6?+
Yes. Per agent turn, Kimi K3.1 Pro Highspeed costs about $0.60 against $0.75 for Claude Opus 4.6 — 20% less.
05What is the context window of Kimi K3.1 Pro Highspeed?+
Kimi K3.1 Pro Highspeed supports a 1M token context window on RouterPlex, the 14th largest of the 69 models that publish one.
06Can I use Kimi K3.1 Pro Highspeed with the OpenAI SDK?+
Yes. RouterPlex serves Kimi K3.1 Pro Highspeed through an OpenAI-compatible endpoint at https://api.routerplex.com/v1 — point any OpenAI SDK or tool at that base URL with your RouterPlex key and set model to "kimi-k3.1-pro-highspeed".
Provider family
More from Moonshot.
Deploy this route
Put Kimi K3.1 Pro Highspeed behind one key.
Top up from $5 with no subscription required.