This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.

Kimi has launched a newer release, Kimi K2 0905. We suggest considering it instead.

All Releases•

Kimi

•

Open weights model

•

Released July 2025

Kimi K2: Intelligence, Performance & Price Analysis

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Try it out

Available providers

Novita

IntelligenceUpdated

N/A

Artificial Analysis Intelligence Index

Performance

Time to first answer token 9.53sOutput speed 34 tok/s

N/A

Time per Intelligence Index task (minutes)

Cost

In $0.57Out $2.30

N/A

Cost per Intelligence Index task

Verbosity

N/A

Output tokens from Intelligence Index

Kimi K2 supports text input, outputs text, and has a 128k tokens context window.

Pricing for Kimi K2 is $0.57 per 1M input tokens (somewhat expensive, median: $0.50) and $2.30 per 1M output tokens (somewhat expensive, median: $1.59).

Reasoning	No
Input modality	Supports: text
Output modality	Supports: text
Context window	128k ~192 A4 pages of size 12 Arial font
Total parameters	1T
Active parameters	32B Number of parameters active per token during inference
License	Modified MIT License
Model weights	Hugging Face

Metrics are compared against models of the same class:

Non-reasoning models → compared only with other non-reasoning models
Reasoning models → compared across both reasoning and non-reasoning
Open weights models → compared only with other open weights models of the same size class:

Tiny: ≤4B parameters
Small: 4B–40B parameters
Medium: 40B–150B parameters
Large: >150B parameters

Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:

<$0.15 per 1M tokens
$0.15–$1 per 1M tokens
>$1 per 1M tokens

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

No publicly available API

Time per Task

Inference time (minutes) per Intelligence Index task · Lower is better

No publicly available API

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

No publicly available API

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Intelligence Index vs. Cost per Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Performance

Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Output Speed

Output tokens divided by total request time, including time to first token · Higher is better

Output tokens, including reasoning tokens, received per second over a request's full duration, from sending the request to receiving the final token. The headline value averages each Performance v3 workload over the past 5 days, then averages the workloads.

Time to First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Context Window

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference (billions)

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Further details

								Weights
Kimi K2	Kimi	-	1T 32B active at inference time	128k	$0.74	-	34	🤗

Frequently Asked Questions

Common questions about Kimi K2

Kimi K2 was released on July 11, 2025.

Kimi K2 was created by Kimi.

Kimi K2 has a time to first answer token of 9.53s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 2.58s).

Kimi K2 costs $0.57 per 1M input tokens (somewhat higher than average, median: $0.50) and $2.30 per 1M output tokens (somewhat higher than average, median: $1.59), based on the median across providers serving the model.

Kimi K2 costs $0.57 per 1M input tokens and $2.30 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.74 per 1M tokens. Pricing may vary by provider. Compare provider pricing

No, Kimi K2 is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Kimi K2 supports text input.

Kimi K2 supports text output.

No, Kimi K2 does not support image input. It can only process text.

No, Kimi K2 is not multimodal. It only supports text input.

Kimi K2 has a context window of 128k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Kimi K2 is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Kimi K2 has 1T parameters (32B active).

Kimi K2 is a Mixture of Experts (MoE) model with 1T total parameters, but only 32B active parameters are used during inference.

Kimi K2 is released under the Modified MIT License license. Commercial use is allowed with restrictions. View license

Yes, Kimi K2 is available via API through 1 provider. Compare API providers

Kimi K2 is available through 1 API provider. Compare providers

Kimi K2: Intelligence, Performance & Price Analysis

Model summary

IntelligenceUpdated

Performance

Cost

Verbosity

Technical specifications

47 models in this class

Intelligence

Time per Task

Cost per Task

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index

Open Weights

Intelligence Index vs. Cost per Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Openness Index

Artificial Analysis Openness Index: Score

Cost

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Cache Hit

Performance

Time per Intelligence Index Task

Time per Intelligence Index Task

Time Period

Output Speed

End-to-End Output Speed

Time to First Answer Token

Time to First Answer Token

Context Window

Context Window

Context Window for RAG

Context Window

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Further details

More from Kimi

Frequently Asked Questions

When was Kimi K2 released?

Who created Kimi K2?

What is the latency of Kimi K2?

How much does Kimi K2 cost?

What is Kimi K2 API pricing?

Is Kimi K2 a reasoning model?

What input modalities does Kimi K2 support?

What output modalities does Kimi K2 support?

Can Kimi K2 process images?

Is Kimi K2 multimodal?

What is the context window of Kimi K2?

Is Kimi K2 open source?

How many parameters does Kimi K2 have?

What are the active parameters of Kimi K2?

What is the license for Kimi K2?

Is Kimi K2 available via API?

Where can I use Kimi K2?