Proprietary model
Released July 2026
Kimi K3 Intelligence, Performance & Price Analysis
Model summary
IntelligenceUpdated
Speed
Price
Cache Hit Price
Verbosity
Comparison Summary
Kimi K3 is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. It's also slower than average and very verbose. The model supports text and image input, outputs text, and has a 1M tokens context window.
Kimi K3 scores 57 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (averaging 30). When evaluating the Intelligence Index, it generated 130M tokens, which is very verbose in comparison to the average of 63M.
Pricing for Kimi K3 is $3.00 per 1M input tokens (somewhat expensive, average: $1.75) and $15.00 per 1M output tokens (somewhat expensive, average: $8.40). In total, it cost $2690.80 to evaluate Kimi K3 on the Intelligence Index.
At 62 tokens per second, Kimi K3 is slower than average (73).
Technical specifications
This page shows the reasoning version of this model.
A non-reasoning variant may also exist.
Supports: text, image
Supports: text
189 models in this class
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
Highlights
Intelligence
Speed
Cost per Task
IntelligenceUpdated
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Intelligence Index methodology
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Intelligence Index methodology
Open Weights
Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).
Intelligence Breakdown
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
AA-Omniscience Non-Hallucination Rate
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, task all-pass rate
Agentic business operations
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence Evaluation Relevance
While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Intelligence Index methodology
AA-BriefcaseNew
AA-Briefcase Elo
AA-Briefcase Elo
AA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.
AA-Omniscience
AA-Omniscience Index
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.
Intelligence Index Comparisons
Intelligence vs. Cost per Intelligence Index Task
Cost per Intelligence Index Task
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.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Intelligence Index methodology
Token Use
Output Tokens per Intelligence Index Task
Output Tokens per Intelligence Index Task
The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).
Price and Cost
Cost per Intelligence Index Task
Cost per Intelligence Index Task
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.
Cost to Run Artificial Analysis Intelligence Index
Cost to Run 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
Cache Hit
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.
Input Price
Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Cache Pricing by Provider
The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:
Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.
See Prompt Caching for the full breakdown.
Output Price
Price per token generated by the model (received from the API), represented as USD per million Tokens.
Model Performance Representation
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Context Window
Context Window
Context Window for RAG
Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.
Context Window
Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Speed
Measured by Output Speed (tokens per second)
Output Speed
Output Speed
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Model Performance Representation
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Time per Intelligence Index Task
Time per Intelligence Index Task
The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
Time to First Answer Token
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.
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
End-to-End Response Time
Seconds to receive a 500 token response. Key components:
Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed
Model Performance Representation
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Frequently Asked Questions
Common questions about Kimi K3
When was Kimi K3 released?
Kimi K3 was released on July 16, 2026.
Who created Kimi K3?
Kimi K3 was created by Kimi.
How intelligent is Kimi K3?
Kimi K3 scores 57 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 30).
How fast is Kimi K3?
Kimi K3 generates output at 62.0 tokens per second (based on Kimi's API), which is below average compared to other reasoning models in a similar price tier (median: 72.7 t/s).
What is the latency of Kimi K3?
Kimi K3 has a time to first token (TTFT) of 1.99s (based on Kimi's API), which is better than average compared to other reasoning models in a similar price tier (median: 2.60s).
How much does Kimi K3 cost?
Kimi K3 costs $3.00 per 1M input tokens (somewhat higher than average, median: $1.75) and $15.00 per 1M output tokens (somewhat higher than average, median: $8.40), based on Kimi's API.
What is Kimi K3 API pricing?
Kimi K3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens (based on Kimi's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $2.31 per 1M tokens. Pricing may vary by provider. Compare provider pricing
How verbose is Kimi K3?
When evaluated on the Intelligence Index, Kimi K3 generated 130M output tokens, which is at the higher end compared to other reasoning models in a similar price tier (median: 63M).
Is Kimi K3 a reasoning model?
Yes, Kimi K3 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Kimi K3 support?
Kimi K3 supports text and image input.
What output modalities does Kimi K3 support?
Kimi K3 supports text output.
Can Kimi K3 process images?
Yes, Kimi K3 supports image input and can analyze, describe, and answer questions about images.
Is Kimi K3 multimodal?
Yes, Kimi K3 is multimodal. It can process text and image input and generate text output.
What is the context window of Kimi K3?
Kimi K3 has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is Kimi K3 open source?
No, Kimi K3 is proprietary. The model weights are not publicly available.
How many parameters does Kimi K3 have?
Kimi K3 has 2.8 trillion parameters.
How does Kimi K3 perform on benchmarks?
Kimi K3 achieves a score of 57 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Kimi K3 available via API?
Yes, Kimi K3 is available via API through 1 provider. Compare API providers
Where can I use Kimi K3?
Kimi K3 is available through 1 API provider. Compare providers