Moonshotai

Kimi K2 Thinking API Pricing 2026

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

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Kimi K2 Thinking was released on November 6, 2025. Pricing starts at $0.600 per million input tokens and $2.50 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$0.600
Output$2.50
Cached$0.150
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ReasoningToolsCaching

Kimi K2 Thinking is priced at $0.600 per million input tokens and $2.50 per million output tokens. It has a context window of 131,072 tokens. It is available from 4 providers, with Amazon Bedrock the cheapest at $0.600 per million input tokens.

Pricing Comparison

Compare Kimi K2 Thinking with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.600
$2.500
—
—
—
131,072
Try
$0.510
$0.740
—
—
—
8,192
Try
$0.520
$2.080
—
—
—
131,072
Try
$0.550
$2.200
—
—
—
131,000
Try
$0.550
$0.800
—
—
—
32,768
Try
$0.550
$2.190
—
—
—
64,000
Try
$0.550
$2.200
—
—
—
128,000
Try
$0.570
$1.420
—
—
—
256,000
Try
$0.600
$3.000
—
—
—
262,144
Try
$0.600
$1.920
—
—
—
202,752
Try
$0.600
$1.000
—
—
—
4,096
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.

4
Providers
$0.600
Cheapest Input/M
$2.500
Cheapest Output/M
Amazon Bedrock
Best Price

Provider Pricing

4 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Amazon Bedrock
Amazon Bedrock
Best Price
$0.600
$2.500
-
-
-
Fireworks
Fireworks
Best Price
$0.600
$2.500
-
-
-
Novita
Novita
Best Price
$0.600
$2.500
$0.150
-
100.0%
OpenRouter
OpenRouter
Best Price
$0.600
$2.500
$0.150
-
-
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...
Other models

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

Frequently Asked Questions

Kimi K2 Thinking costs $0.000600 per 1,000 input tokens and $0.002500 per 1,000 output tokens.
Kimi K2 Thinking is available from 4 providers. Amazon Bedrock offers the best price.
Amazon Bedrock offers Kimi K2 Thinking at $0.600 per million input tokens.
We compare Kimi K2 Thinking with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Moonshotai Models

See pricing for all Moonshotai models.

View all Moonshotai models →