Moonshotai model

Kimi K3 API

Send moonshotai/kimi-k3 when you need the long-window Kimi id: 1,048,576 tokens at 2.95 / 14.71, with streaming, tools, JSON, and vision listed. K2.5 CN and K2.6 CN are cheaper and do not publish a context window. CacheSafety is unpublished for K3.

Read quickstartEstimate cost
MoonshotaiPlatform curatedCatalog
ThinkingVision
Input price$2.95 / 1M tokens
Output price$14.71 / 1M tokens
Context length1M tokens
Max output8.2k tokens

What is Kimi K3 API in NextModel?

Send moonshotai/kimi-k3 when you need the long-window Kimi id: 1,048,576 tokens at 2.95 / 14.71, with streaming, tools, JSON, and vision listed. K2.5 CN and K2.6 CN are cheaper and do not publish a context window. CacheSafety is unpublished for K3.

Kimi K3 via NextModel: 1M-token context; $2.95 / 1M tokens in / $14.71 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Best use cases

  • Kimi jobs that need a published million-class window.
  • Vision or tool calls the CN Kimi ids do not list.
  • A flagship Kimi id beside cheaper K2.5 CN at 0.58 / 3.02.

When not to use

  • You wanted cheap Chinese Kimi tokens. Start with K2.5 CN.
  • You need cache scores. K3 has no first-party row.
  • You cannot spend 14.71 on output tokens.

OpenAI-compatible code example

request.sh
curl https://api.nextmodel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -d '{"model":"moonshotai/kimi-k3","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

GoogleCatalog

Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite via NextModel: 1M-token context; $0.3 / 1M tokens in / $2.50 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$0.3 / 1M tokensInput$2.50 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
GoogleCatalog

Gemini 3.6 Flash

Gemini 3.6 Flash via NextModel: 1M-token context; $1.50 / 1M tokens in / $7.50 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$1.50 / 1M tokensInput$7.50 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-5.6 Luna

GPT-5.6 Luna via NextModel: 1M-token context; Starting at $0.2 / 1M tokens in / $1.20 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Starting at $0.2 / 1M tokensInput$1.20 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare Kimi K3

Kimi K3 vs Gemini 3.5 Flash-LiteKimi K3 vs Gemini 3.6 FlashKimi K3 vs GPT-5.6 LunaKimi K3 vs GPT-5.6 SolKimi K3 vs GPT-5.6 Terra

Reading

Articles that explain Kimi K3

FAQ

Kimi K3 API questions

What model id do I send for Kimi K3?

Send moonshotai/kimi-k3 to https://api.nextmodel.app/v1.

Why not K2.5 CN?

K2.5 CN is 0.58 / 3.02 with unpublished context and only streaming listed. K3 publishes 1,048,576 tokens plus tools and vision.

CacheSafety?

Unpublished for this exact id.

Start now

Ready to start building?

Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.

Get your API keyRead the quickstart