Kimi

•

Kimi K3

•

Open weights model

•

Released July 2026

Kimi K3 (Low) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Kimi K3 (Low) for your use-case.

Fastest

Inco (FAST)

342.9 t/s

Nebius

154.7 t/s

Fireworks

111.5 t/s

Databricks

100.4 t/s

Baseten

97.1 t/s

Output speed

Total 8 providers

Lowest Latency

Inco (FAST)

7.61 s

Nebius

14.05 s

Fireworks

18.94 s

Databricks

20.85 s

Baseten

21.66 s

Time to first answer token

Total 8 providers

Lowest Price

Kimi

$2.31

Baseten

$2.31

Databricks

$2.31

DigitalOcean

$2.31

Fireworks

$2.31

Blended price (per 1M tokens)

Total 8 providers

Kimi K3 (low) is available through 8 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

For output speed, the top providers are Inco (FAST) (342.9 t/s), Nebius (154.7 t/s), and Fireworks (111.5 t/s). Speed varies significantly across providers, with a 1091% difference between the fastest and slowest.
For latency, Inco (FAST) (7.61s), Nebius (14.05s), and Fireworks (18.94s) offer the lowest time to first answer token.
For pricing, Kimi (2.31), Baseten (2.31), and Databricks (2.31) offer the lowest blended prices per 1M tokens.
Inco (FAST) offers the best performance with both the highest speed and lowest latency. For cost optimization, Kimi provides the most competitive pricing.

Speed

Output tokens per second · Higher is better

Latency

Seconds to first answer token received · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.

Pricing

Pricing: Cache Hit, Input, and Output: Kimi K3 (low) Providers

Price (USD per M Tokens) · Lower is better · 10,000 input 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.

Cost per Intelligence Index Task: Kimi K3 (low) Providers

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

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.

Output Speed vs. Price: Kimi K3 (low) Providers

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

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).

Speed

Measured by Output Speed (tokens per second)

Output Speed: Kimi K3 (Low)

Output speed: output tokens per second · 10,000 input tokens

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).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Time per Intelligence Index Task: Kimi K3 (low) Providers

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

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.

Cost per Task vs. Time per Task: Kimi K3 (low) Providers

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

Pareto line

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token: Kimi K3 (low) Providers

Seconds to first token received · Lower is better · 10,000 input tokens

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.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Cache Behaviour

Cache Hit Rate: Kimi K3 (low) Providers

Share of cacheable input tokens served from cache · Median of the last four weeks, updated Sep 26, 2026

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic coding sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate: Kimi K3 (low) Providers

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Sep 26, 2026

Most attractive quadrant

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: Kimi K3 (low) Providers

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

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

Key Comparison Metrics & API Features



Kimi	1.05M	Open	$1.15	40	3.75	66.23	49.99
Baseten	1M	Open	$1.41	97	1.06	26.81	20.61
Databricks	1M	Open	$0.88	100	0.92	25.83	19.92
Nebius	1.05M	Open	$5.77	155	1.12	17.28	12.93
DigitalOcean	1M	Open	$0.92	64	1.12	40.48	31.48
Fireworks	1.05M	Open	$0.92	111	0.99	23.42	17.94
Inco	1.05M	Open	$1.81	343	1.77	9.06	5.83
Inco	1M	Open	$0.91	29	17.22	104.04	69.46

Frequently Asked Questions

Common questions about Kimi K3 (Low) providers

Kimi K3 (Low) is available through 8 API providers: Kimi, Baseten, Databricks, Nebius, DigitalOcean, Fireworks, Inco (FAST), and Inco. Each provider offers different performance characteristics and pricing.

Kimi K3 (Low) is currently available through 8 API providers that we benchmark and track.

The fastest providers for Kimi K3 (Low) by output speed are Inco (FAST) (342.9 t/s), Nebius (154.7 t/s), and Fireworks (111.5 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first answer token for Kimi K3 (Low) are Inco (FAST) (7.61s), Nebius (14.05s), and Fireworks (18.94s). Lower latency means faster initial response time.

The most affordable providers for Kimi K3 (Low) by blended price are Kimi ($2.31 per 1M tokens), Baseten ($2.31 per 1M tokens), and Databricks ($2.31 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The providers with the lowest input token pricing for Kimi K3 (Low) are Kimi ($3.00 per 1M input tokens), Baseten ($3.00 per 1M input tokens), and Databricks ($3.00 per 1M input tokens).

The providers with the lowest output token pricing for Kimi K3 (Low) are Kimi ($15.00 per 1M output tokens), Baseten ($15.00 per 1M output tokens), and Databricks ($15.00 per 1M output tokens).

Prices for Kimi K3 (Low) vary up to 2.0x across providers. The most affordable is Kimi at $2.31 per 1M tokens, while Inco (FAST) charges $4.62 per 1M tokens.

Output speed for Kimi K3 (Low) varies significantly across providers. Inco (FAST) is the fastest at 342.9 t/s, which is 11.9x faster than Inco at 28.8 t/s.

All 8 providers of Kimi K3 (Low) support JSON mode for structured output.

All 8 providers of Kimi K3 (Low) support function calling (tool use).

For Kimi K3 (Low), Inco (FAST) offers the best performance with highest speed and lowest latency. For cost optimization, Kimi provides the most competitive pricing.

When choosing a provider for Kimi K3 (Low), consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about Kimi K3 (Low)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview

Kimi K3 (Low) API Provider Benchmarking & Analysis

Fastest

Lowest Latency

Lowest Price

Speed

Latency

Price

Pricing

Pricing: Cache Hit, Input, and Output: Kimi K3 (low) Providers

Cache Hit

Cost per Intelligence Index Task: Kimi K3 (low) Providers

Cost per Intelligence Index Task

Output Speed vs. Price: Kimi K3 (low) Providers

Output Speed

Speed

Output Speed: Kimi K3 (Low)

Output Speed

Model Performance Representation

Time per Intelligence Index Task: Kimi K3 (low) Providers

Time per Intelligence Index Task

Cost per Task vs. Time per Task: Kimi K3 (low) Providers

Cost per Intelligence Index Task

Latency

Time to First Answer Token: Kimi K3 (low) Providers

Time to First Answer Token

Median

Cache Behaviour

Cache Hit Rate: Kimi K3 (low) Providers

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate: Kimi K3 (low) Providers

Cost per Intelligence Index Task

End-to-End Response Time

End-to-End Response Time: Kimi K3 (low) Providers

End-to-End Response Time

Key Comparison Metrics & API Features

Frequently Asked Questions

Where can I access Kimi K3 (Low)?

How many API providers offer Kimi K3 (Low)?

Which provider is fastest for Kimi K3 (Low)?

Which provider has the lowest latency for Kimi K3 (Low)?

Which provider is cheapest for Kimi K3 (Low)?

Which provider has the lowest input price for Kimi K3 (Low)?

Which provider has the lowest output price for Kimi K3 (Low)?

How much do prices vary across Kimi K3 (Low) providers?

How much does speed vary across Kimi K3 (Low) providers?

Which Kimi K3 (Low) providers support JSON mode?

Which Kimi K3 (Low) providers support function calling?

Which is the best provider for Kimi K3 (Low)?

How do I choose a provider for Kimi K3 (Low)?

Does provider performance for Kimi K3 (Low) change over time?

What are the overall capabilities of Kimi K3 (Low)?