Skip to content
Kimi

Kimi K3.1 PRO

inworld/models/kimi-k3.1-pro

Kimi K3.1 PRO is a reasoning model by Kimi with vision, function calling, prompt caching, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 1M token context window with up to 1M tokens of output. Priced at $2 per million input tokens and $10 per million output tokens. Access Kimi K3.1 PRO through Inworld LLM Inference with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

Input
$2.00
Output
$10.00
Cache read
$0.20
Context
1M
Max output
1M
TextImage→Text
Function CallingReasoningPrompt CachingStructured outputVision
Run on your server. Set INWORLD_API_KEY to your API key. Python requires pip install openai; JavaScript requires Node.js 18+; save it as example.mjs.
curl --fail-with-body https://api.inworld.ai/v1/chat/completions \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "inworld/models/kimi-k3.1-pro",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'
Model Kimi K3.1 PROOpenAI SDK compatible

Pricing and providers

Access Kimi K3.1 PRO through Inworld LLM Inference or speech to speech via Inworld. By using the providers below you agree to their terms, listed under each provider's name in the Legal section.

Modalities
InworldThis pageinworld/models/kimi-k3.1-pro
$2.00$10.00$0.20—1M1M
TextImage→Text
Prices in USD per 1M tokens.

Start building with Kimi K3.1 PRO

Access Kimi K3.1 PRO and every other model through LLM Inference or speech to speech. Create a free account and start in minutes.