Experiential
ModelsLogsInsights
Star us on GitHubDocsSettings
Sign in
Continue with GoogleContinue with GitHub
or
Models

Kimi K2.6

kimi-k2.6by Kimi
CompareOpen in Playground

Context

262K

Max output

262K

Pricing

$0.54/M in$0.16/M cached$2.28/M out

Waterfall

Supported parameters

primary route

Sampling

Status
Azure Foundry via Experiential CloudexperientialKimi-K2.62143 tok/s1.01s4.2%262K262K$0.95$4cache$0.16——activemeasured
Fireworks via Experiential Cloudexperiential———262K262K$0.95$4cache$0.16—ZDRactiveestimated
TTencent Cloud via Experiential Cloudexperiential———262K262K$0.95$4cache$0.16——active—
WWafer via Experiential Cloudexperiential———262K262K$1.14$4.80cache$0.19——active—
Azure FoundryFW-Kimi-K2.62143 tok/s1.01s4.2%262K262K$0.95≈$4≈cache$0.16≈——activemeasured
Azure FoundryKimi-K2.6-2026-04-20deployed 2026-04-202143 tok/s1.01s4.2%262K262K$0.95≈$4≈cache$0.16≈——activemeasured

Fastest

2143 tok/s

Released

Apr 2026

Temperature0–2Top-p0.01–1Stop sequences

Tools & structure

Tools*Parallel tool calls*Structured output

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

* not supported on every route; the gateway adapts or drops it (with a warning) on stricter providers.

Shown for the primary route; fallback routes may differ. Sending an unsupported field? See error reference.

Azure OpenAI docs

Quickstart

I want you to route my LLM calls for "kimi-k2.6" through the Experiential gateway instead of
calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL
and key swap. Please:

1. Point the client at https://api.experientiallabs.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If
   it isn't set, stop and tell me to create one under Settings -> API Keys and export it.
3. Use the model id "kimi-k2.6" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key,
   leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my
   Experiential credits.

Tell me which files you changed.

Set EXPLABS_API_KEY to an organization API key before running your agent.

Benchmarks

Hugging Face
  • MMLU-Propaper · Aug 202688.1%
  • GPQA DiamondHugging Face · Aug 202690.5%
  • SWE-bench VerifiedHugging Face · Aug 202680.2%
  • LiveBenchpublic leaderboard · Aug 202670.5%
  • AIME 2026Hugging Face · Aug 202696.4%
  • Humanity's Last ExamHugging Face · Aug 202634.7%
  • LMArena EloLMArena · Aug 20261455
  • Terminal-BenchHugging Face · Aug 202666.7