ElevenRouter
Get started
Moonshot AI

Kimi K2.6

moonshotai/kimi-k2.6Operational

Moonshot AI Kimi K2.6: general-purpose model with a 256K context window, text/image/video input, and both thinking and non-thinking modes.

Open in request builderTry in playground
Input
$0.950
per 1M tokens
Output
$4.00
per 1M tokens
Cache read
$0.160
per 1M tokens
Context
262K
tokens
Max output
33K
tokens
Official pricing

USD per million tokens, exactly what Moonshot AI publishes. ElevenRouter adds nothing on tokens.

Input$0.950
Output$4.00
Cache read$0.160
Cache write$0.950
Example · 1,000 in + 500 out$0.00295
Capabilities
  • Tool calling
  • Structured outputs
  • JSON mode
  • Reasoning
  • Vision
  • Audio input
  • Prompt caching
  • Streaming
Modalities
text+image->text
Tokenizer
Kimi
Released
2026-09-25
Family
kimi-k
Availability

Measured by the routing engine; up when at least one credential can serve the model.

Last 3 days
99.82%
Last 30 days
99.82%
30 days agotoday
Full status page
Observed performance

Real requests over the last 7 days.

TTFT p50
—
TTFT p95
—
Tokens / s p50
—
Tokens / s p95
—

Percentiles appear after five successful requests.

Usage on ElevenRouter

Tokens per day across all customers, anonymous and aggregate.

0 tokens · 30d
0 requests in the last 7 days
Use it

Any OpenAI or Anthropic SDK works by changing the base URL. Supported parameters: max_tokens, temperature, top_p, top_k, frequency_penalty, presence_penalty, repetition_penalty, seed, stop, tools, tool_choice, response_format, reasoning, include_reasoning.

curl https://elevenrouter.com/api/v1/chat/completions \
  -H "Authorization: Bearer $ELEVENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "moonshotai/kimi-k2.6", "messages": [{ "role": "user", "content": "Hello" }] }'
Request builderFallbacks & variantsSDKs
Related models

Questions

How much does Kimi K2.6 cost on ElevenRouter?
Kimi K2.6 is billed at Moonshot AI's official list price: $0.950 per million input tokens and $4.00 per million output tokens, with cached input at $0.160. A request with 1,000 input and 500 output tokens costs about $0.00295.
What is the context length of Kimi K2.6?
Kimi K2.6 accepts up to 262K tokens of context and can produce up to 33K output tokens.
Does Kimi K2.6 support tool calling and structured outputs?
Yes, tool calling is supported and JSON mode is available; add the response-healing plugin for schema validation. Supported parameters: max_tokens, temperature, top_p, top_k, frequency_penalty, presence_penalty, repetition_penalty, seed, stop, tools, tool_choice, response_format, reasoning, include_reasoning.
How do I call Kimi K2.6?
Send an OpenAI-compatible chat completion to https://elevenrouter.com/api/v1/chat/completions with "model": "moonshotai/kimi-k2.6" and your ElevenRouter key, or use the Anthropic Messages endpoint. Any OpenAI or Anthropic SDK works by changing the base URL.
Is Kimi K2.6 available right now?
Availability is measured continuously by the routing engine. Current status: operational, 99.82% uptime over the last 30 days. When one credential fails, requests fail over to another automatically.