Kimi K2 Thinking API Pricing 2026

Compare pricing, benchmarks, and providers for Kimi K2 Thinking. Find the best value for your use case.

Best Coding Model Leaderboard— Find the top LLM for coding by benchmarks and community votes

114 out of our 298 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Last updated: February 24, 2026 at 08:07 AM

Overview

Kimi K2 Thinking was released on November 6, 2025. Pricing starts at $0.470 per million input tokens and $2.00 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through Moonshotai.

Context Window

131K

tokens

Pricing

Input$0.470

Output$2.00

Cached$0.141

per 1M tokens

Speed

Output78 tok/s

TTFT0.68s

median latency

Capabilities

ReasoningToolsCaching

Pricing Comparison

Compare Kimi K2 Thinking with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Coding	MMLU	GPQA	Context	Actions
MS Moonshotai	Kimi K2 Thinking	$0.470	$2.000	85.3	84.8	83.8	131,072	Try
MI Mistral AI	Mistral Medium 3	$0.400	$2.000	40.0	76.0	57.8	131,072	Try
O OpenAI	GPT-4.1 Mini	$0.400	$1.600	48.3	78.1	66.4	1,047,576	Try
QW Qwen	Qwen-Plus	$0.400	$1.200	—	—	—	1,000,000	Try
DS Deepseek	DeepSeek V3.2 Speciale	$0.400	$1.200	89.6	86.3	87.1	163,840	Try
TD Thedrummer	UnslopNemo 12B	$0.400	$0.400	—	—	—	32,768	Try
M Meta-llama	Llama 3.1 70B Instruct	$0.400	$0.400	23.2	67.6	40.9	131,072	Try
BD Baidu	ERNIE 4.5 VL 424B A47B	$0.420	$1.250	—	—	—	123,000	Try
MS Moonshotai	Kimi K2.5	$0.450	$2.200	—	—	78.9	262,144	Try
U9 Undi95	ReMM SLERP 13B	$0.450	$0.650	—	—	—	6,144	Try
QW Qwen	Qwen3 235B A22B	$0.455	$1.820	34.3	76.2	61.3	131,072	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Kimi K2 Thinking is available from multiple providers with different pricing and availability.

Providers

$0.470

Cheapest Input/M

$2.000

Cheapest Output/M

DeepInfra

Best Price

Provider Pricing

12 models

Provider	Input $/M	Output $/M	Cache Read $/M	Cache Write $/M	Uptime
DeepInfra Best Price	$0.470	$2.000	$0.141	-	100.0%
P Parasail	$0.500	$2.500	-	-	-
S SiliconFlow	$0.550	$2.500	-	-	-
A AtlasCloud	$0.600	$2.500	$0.600	-	-
Nebius	$0.600	$2.500	-	-	-
Amazon Bedrock	$0.600	$2.500	-	-	-
B BaseTen	$0.600	$2.500	-	-	-
Fireworks	$0.600	$2.500	-	-	-
Moonshot AI	$0.600	$2.500	$0.150	-	-
Google	$0.600	$2.500	-	-	100.0%
Novita	$0.600	$2.500	$0.150	-	-
Together	$1.200	$4.000	-	-	-

Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Kimi K2 Thinking perform? Vote based on your experience.

Cost vs. Quality

Compare Kimi K2 Thinking's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

Kimi K2 Thinking

Other models

Detailed Benchmark Scores

Intelligence

40.7 (90th pct)

Coding

34.8 (86th pct)

Math

94.7 (94th pct)

MMLU Pro

84.8 (86th pct)

GPQA

83.8 (90th pct)

LiveCodeBench

85.3 (94th pct)

AIME

Aider

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Kimi K2 Thinking

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Kimi K2 Thinking directly in your browser.

Open Playground

Compare Kimi K2 Thinking

Frequently Asked Questions

All Moonshotai Models

See pricing for all Moonshotai models.

View all Moonshotai models →