How much does Kimi K2.6 cost?

On the Respan gateway, input starts at $0.65 per 1M tokens on OpenRouter, and output starts at $3.40 per 1M tokens on Featherless and Novita, after gateway discounts. Averaged across its 13 routes from 12 providers, it costs $0.89 per 1M input tokens and $3.85 per 1M output tokens.

Which providers serve Kimi K2.6 on Respan?

Kimi K2.6 is available through 13 routes from 12 providers: OpenRouter, DeepInfra, Parasail, Featherless, Novita, IO.net, and 6 more. Tera and TogetherAI require your own provider API key (BYOK).

What is Kimi K2.6's context window?

Kimi K2.6 accepts up to 262K tokens of context on its largest provider route.

How do I use Kimi K2.6 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "moonshot/kimi-k2.6". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Kimi K2.6?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Parasail at 112 tokens per second, and the lowest response latency was 0.7 seconds on IO.net. Speed varies with request size and provider.

Where does Kimi K2.6 rank on the Respan Index?

Kimi K2.6 scores 34.4 out of 100 on the Respan Index v1.1, ranking #55 of 138 models. By category: Coding 13.9, Agents 45.1, Reasoning 32.9, Knowledge & language 34.8, and Human preference 52.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Kimi K2.6 score on benchmarks?

Kimi K2.6 has 35 published benchmark scores, including LiveBench Coding 78.6%, OSWorld-Verified 73.1%, and GPQA Diamond 90.8%. Each score links to where it was published; the data is collected by llmmetric.com.

DemoBook a demo Dashboard

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Copy for agentRead docs

Providers

Kimi K2.6 API: Pricing, Benchmarks & Context Window | Respan

Kimi K2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.

Input / output, from: $0.65 / $3.40 per 1M
Context: 262K tokens
Released: Apr 20, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "moonshot/kimi-k2.6".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="moonshot/kimi-k2.6",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "moonshot/kimi-k2.6",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "moonshot/kimi-k2.6",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

13 routes from 12 providers, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read
OpenRouter`openrouter/moonshotai/kimi-k2.6`	262K	$0.65/M	$3.41/M	$0.15/M
DeepInfra`deepinfra/moonshotai/Kimi-K2.6`	262K	$0.75/M	$3.50/M	$0.15/M
Parasail`parasail/moonshotai/Kimi-K2.6`	262K	$0.75/M	$3.50/M	$0.16/M
Parasail`parasail/parasail-kimi-k26`	262K	$0.75/M	$3.50/M	$0.16/M
Featherless`featherless_ai/moonshotai/Kimi-K2.6`	262K	$0.80/M	$3.40/M	$1.00/M
Novita`novita/moonshotai/kimi-k2.6`	262K	$0.80/M	$3.40/M	$0.16/M
IO.net`ionet/moonshotai/Kimi-K2.6`	262K	$0.86/M	$3.78/M	$0.43/M
EmpirioLabs`empiriolabs/kimi-k2-6`	256K	$0.89/M	$3.71/M	$0.18/M
Moonshot`moonshot/kimi-k2.6`	262K	$0.95/M	$4.00/M	$0.16/M
Nebius`nebius/moonshotai/Kimi-K2.6`	262K	$0.95/M	$4.00/M	$0.00/M
TeraBYOK only`tera/moonshotai/Kimi-K2.6`	262K	$0.95/M	$4.00/M	$0.16/M
TogetherAIBYOK only`together_ai/moonshotai/Kimi-K2.6`	262K	$1.20/M	$4.50/M	$0.20/M
Inference.net`inference_net/kimi-k2.6`	262K	$1.25/M	$5.30/M	$0.21/M

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

Benchmarks

The Respan Index plus 35 published scores from 10 sources, each linked to where it was published.

34.4/ 100

Respan Index#55 of 138

138 ranked models. The shaded band is this model's 95% interval, 30.0 to 39.7. Claude Sonnet 4.6 and GLM-5.1 fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
LiveBench CodingLiveBench	78.6%	LiveBench	Oct 5, 2026
SWE-bench VerifiedEpoch AI	76.7%	Epoch AI	Oct 5, 2026
WeirdMLHåvard Tveit Ihle	55.9%	Håvard Tveit Ihle	Oct 5, 2026
Kimi Code Bench v2kimi.com	50.9%	kimi.com	Jun 12, 2026
ProgramBenchkimi.com	48.3%	kimi.com	Jun 12, 2026
MLS-Bench-Litekimi.com	26.7%	kimi.com	Jun 12, 2026

Benchmark	Score	Source	Published
OSWorld-VerifiedXLANG	73.1%	XLANG	Apr 20, 2026
MCPMark-Verifiedkimi.com	72.8%	kimi.com	Jun 12, 2026
MCP-Atlaskimi.com	69.4%	kimi.com	Jun 12, 2026
Toolathlon-VerifiedHKUST	58%	HKUST	Jul 15, 2026
LiveBench Agentic CodingLiveBench	46.9%	LiveBench	Oct 5, 2026
Kimi Claw 24/7 Benchkimi.com	42.9%	kimi.com	Jun 12, 2026
Vending-Bench 2Andon Labs	6204.57 · #18 of 59	Andon Labs	Oct 5, 2026

Benchmark	Score	Source	Published
GPQA DiamondEpoch AI	90.8%	Epoch AI	Oct 5, 2026
LiveBench ReasoningLiveBench	79.4%	LiveBench	Oct 5, 2026
LiveBench Data AnalysisLiveBench	65.1%	LiveBench	Oct 5, 2026
Chess PuzzlesEpoch AI	26%	Epoch AI	Oct 5, 2026
Mystery Game PuzzlesEpoch AI	18%	Epoch AI	Oct 5, 2026
EBR-benchEpoch AI	2.4%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	96.1%	Epoch AI	Oct 5, 2026
AIME 2026MathArena	95.8%	MathArena	Sep 17, 2026
LiveBench MathematicsLiveBench	84.3%	LiveBench	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	57.2%	Epoch AI	Oct 5, 2026
FrontierMath Tiers 1-3 v2Epoch AI	57.2%	Epoch AI	Sep 17, 2026
FrontierMath Tier 4 v2Epoch AI	25.6%	Epoch AI	Oct 5, 2026
FrontierMath Tier 4 v2Epoch AI	25.6%	Epoch AI	Sep 17, 2026

Benchmark	Score	Source	Published
LiveBench LanguageLiveBench	75.1%	LiveBench	Oct 5, 2026
LiveBench Instruction FollowingLiveBench	64.4%	LiveBench	Oct 5, 2026
SimpleQA VerifiedEpoch AI	34.9%	Epoch AI	Oct 5, 2026
SimpleQA VerifiedEpoch AI	34.9%	Epoch AI	Sep 17, 2026

Benchmark	Score	Source	Published
Furniture AssemblyEpoch AI	21.7%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1509 Elo · #39 of 94	LMArena	Oct 1, 2026
LMArena EloLMArena	1461 Elo · #41 of 141	LMArena	Oct 2, 2026
LMArena VisionLMArena	1265 Elo · #29 of 77	LMArena	Oct 2, 2026

Benchmark	Score	Source	Published
SAGEVals AI	50.2%	Vals AI	Oct 5, 2026

How the Respan Index works

How Kimi compares: Claude vs Kimi, DeepSeek vs Kimi, Gemini vs Kimi

Providers

Providers

Kimi K2.6

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Index#55 of 138

Published scores

Apps

Kimi K2.6 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Providers

Providers

Kimi K2.6

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Index#55 of 138

Published scores

Apps

Kimi K2.6 FAQ

What is Kimi K2.6?

How much does Kimi K2.6 cost?

Which providers serve Kimi K2.6 on Respan?

What is Kimi K2.6's context window?

How do I use Kimi K2.6 with the Respan gateway?

How fast is Kimi K2.6?

Where does Kimi K2.6 rank on the Respan Index?

How does Kimi K2.6 score on benchmarks?

Works with your entire stack

Built for AI agents. Break less. Ship more.

Built for AI agents.
Break less.
Ship more.