This model was retired on 2027-04-16. The pricing below is the last-known rate, kept for migration reference.

Kimi K2.6Deprecated

MoonshotReleasedJan 1, 1970

VisionTool useReasoningPrompt cachingStructured output

Compare Kimi K2.6

Context

262K

Max output

262K

Serving providers

Cheapest input

$0.65 /1M

Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis and Hugging Face leaderboards

Speed & latency

Output speed

38 t/s

tokens / second

Time to first token

2.88s

latency

Headline indices

Intelligence Index

45.1

of 100

Coding Index

61.8

of 100

Agentic Index

31.2

of 100

Individual benchmarks · click a row for effort variants

Benchmark

Best score

Effort

Cost / task

AA-Briefcase

16%

—

AIME 2026

96%

default

—

APEX Agents

28%

default

—

Automation Bench

0.2

default

—

CritPt

default

—

EvalComputeProxy

2257.5

default

—

GDPval

1190.4

default

—

GPQA Diamond

91%

default

—

Harvey Lab

0.8

default

—

Humanity's Last Exam

37%

default

—

IFBench

76%

default

—

IT-Bench SRE

31%

default

—

Long-Context Reasoning

77%

default

—

MMMU-Pro

79%

default

—

Omniscience

5.3

default

—

Omniscience Accuracy

0.3

default

—

Omniscience Non Hallucination

0.6

default

—

SciCode

53%

default

—

SWE-bench Pro

59%

default

—

SWE-bench Verified

80%

default

—

TerminalBench Hard

44%

default

—

TerminalBench v2.1

66%

default

—

τ-bench Banking

23%

default

—

τ²-bench

96%

default

—

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand

Serving provider

Input /1M

Output /1M

Endpoints

Wandb

$0.65

$3.41

DeepInfra

$0.75

$3.50

Novita

$0.80

$3.40

Azure

$0.95

$4.00

Cloudflare

$0.95

$4.00

Moonshot

$0.95

$4.00

OpenRouter

$0.95

$4.00

Tensormesh

$0.96

$4.00

Price history

input + output $/1M since we started tracking

Input Output

Input down 32% since first tracked

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$403

estimated / month

Model IDs

copy the exact identifier for your platform

wandb/moonshotai/Kimi-K2.6deepinfra/moonshotai/Kimi-K2.6novita/moonshotai/kimi-k2.6azure_ai/kimi-k2.6cloudflare/@cf/moonshotai/kimi-k2.6moonshot/kimi-k2.6moonshotai/kimi-k2.6tensormesh/moonshotai/Kimi-K2.6

Frequently asked questions

Kimi K2.6 pricing, context and availability

Is Kimi K2.6 still available?

Kimi K2.6 was retired on 2027-04-16. The pricing on this page is the last-known rate, kept for migration reference.

How much did Kimi K2.6 cost?

Kimi K2.6's last-known pricing, before it was retired on 2027-04-16, was $0.65 per 1M input tokens and $3.40 per 1M output tokens.

What was the context window of Kimi K2.6?

Kimi K2.6 had a 262K token context window and could return up to 262K output tokens.

What could Kimi K2.6 do?

Kimi K2.6 supported image input (vision), tool use, reasoning, prompt caching and structured output.

Other Moonshot models

compare pricing across the Moonshot lineup

Kimi K2.5$0.45/1M · 8 providers Kimi K2 Thinking$0.60/1M · 7 providers Kimi K2.7 Code$0.66/1M · 7 providers Kimi K3$2.85/1M · 7 providers Kimi K2 Instruct$0.50/1M · 6 providers Kimi K2 Instruct 0905$0.50/1M · 5 providers Kimi K2 0711$0.55/1M · 2 providers Kimi K2 0905$0.60/1M · 2 providers

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI