Moonshot route

kimi-k3.1-pro-abliterated

Kimi K3.1 Pro Abliterated API access.

Moonshot AI's Kimi K3.1 Pro with the refusal behaviour removed from the weights, for authorized security research, red teaming and other work the stock model declines. $4 input and $6.50 output per 1M tokens, cached input $0.65. Preview: 1M context, tool calling, image input, reasoning effort low / high / max. Paid credit only, and the RouterPlex acceptable-use terms still apply. See the Kimi K3.1 Pro Abliterated API pricing notes.

Route status Available

#72

Cost rank / 83

premium

Cost band

Published route economicsUSD / 1M tokens

Input / 1M tokens

$4.00

Output / 1M tokens

$6.50

Cached input / 1M tokens

$0.65

Context window

1M

Provider

Moonshot

An abliterated build of Moonshot AI's Kimi K3.1 Pro: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.

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 72nd cheapest of 83 comparable text models and cheaper than 11 on the same key. Its context window ranks 15th of 83.

Cost simulationPublished base rate

Short request

$0.046

10K input + 1K output

Agent turn

$0.47

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 quickstart
curl /chat/completions
curl https://api.routerplex.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3.1-pro-abliterated",
"messages": [{"role": "user", "content": "Hello!"}]
}'

Route notes

Questions before production traffic.

Same endpoint, every route
01How much does the Kimi K3.1 Pro Abliterated API cost?+

Through RouterPlex, Kimi K3.1 Pro Abliterated costs $4.00 per 1M input tokens and $6.50 per 1M output tokens — RouterPlex's disclosed public reference rate, billed per token from a prepaid balance you top up from $5. Cached input tokens are billed at $0.65 per 1M instead of the full input rate, which is most of the prompt on a repeated agent or coding loop. An abliterated build of Moonshot AI's Kimi K3.1 Pro: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.

02What does one Kimi K3.1 Pro Abliterated agent turn cost?+

A 100K-token input with a 10K-token reply costs about $0.47 on Kimi K3.1 Pro Abliterated. That makes it the 72nd cheapest of 83 comparable text models on RouterPlex, roughly 38.8× the cost of the cheapest option (Muse Spark 1.2 Contributor).

03What is a cheaper alternative to Kimi K3.1 Pro Abliterated?+

Claude Sonnet 4.6 from Anthropic is the closest cheaper model on RouterPlex — $0.45 per agent turn against $0.47 for Kimi K3.1 Pro Abliterated, at $3.00/1M input and $15.00/1M 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 Abliterated cheaper than Grok 4.7 Build Fast?+

Yes. Per agent turn, Kimi K3.1 Pro Abliterated costs about $0.47 against $0.52 for Grok 4.7 Build Fast — 11% less.

05What is the context window of Kimi K3.1 Pro Abliterated?+

Kimi K3.1 Pro Abliterated supports a 1M token context window on RouterPlex, the 15th largest of the 83 models that publish one.

06Can I use Kimi K3.1 Pro Abliterated with the OpenAI SDK?+

Yes. RouterPlex serves Kimi K3.1 Pro Abliterated 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-abliterated".

Deploy this route

Put Kimi K3.1 Pro Abliterated behind one key.

Top up from $5 with no subscription required.