Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Log in

Kimi has launched a newer model, Kimi K2.5, we suggest considering this model instead.

For more information, see Comparison of Kimi K2.5 to other models and API provider benchmarks for Kimi K2.5.

Kimi K2 Thinking logo

Kimi K2 Thinking API Provider Benchmarking & Analysis

Kimi

Open weights model

Released November 2025

Analysis of API providers for Kimi K2 Thinking across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Kimi Turbo, Kimi, Google Vertex, Amazon Bedrock, Nebius (FP8), DeepInfra, Novita, Microsoft Azure.

Fastest

#1
Google VertexGoogle Vertex
251.6 t/s
#2
AmazonAmazon
105.4 t/s
#3
DeepInfraDeepInfra
97.0 t/s
#4
Kimi TurboKimi Turbo
96.9 t/s
#5
AzureAzure
77.5 t/s

Output speed

Total 8 providers

Lowest Latency

#1
Google VertexGoogle Vertex
0.45 s
#2
DeepInfraDeepInfra
0.51 s
#3
AzureAzure
1.15 s
#4
AmazonAmazon
1.27 s
#5
Nebius (FP8)Nebius (FP8)
1.35 s

Time to first token

Total 8 providers

Lowest Price

#1
DeepInfraDeepInfra
$0.85
#2
KimiKimi
$1.07
#3
Google VertexGoogle Vertex
$1.07
#4
AmazonAmazon
$1.07
#5
Nebius (FP8)Nebius (FP8)
$1.07

Blended price (per 1M tokens)

Total 8 providers

Kimi K2 Thinking 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 Google Vertex (251.6 t/s), Amazon (105.4 t/s), DeepInfra (97.0 t/s). Speed varies significantly across providers, with a 225% difference between the fastest and slowest.
  • For latency, Google Vertex (0.45s), DeepInfra (0.51s), Azure (1.15s) offer the lowest time to first token.
  • For pricing, DeepInfra (0.85), Kimi (1.07), Google Vertex (1.07) offer the lowest blended prices per 1M tokens.
  • Google Vertex offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra provides the most competitive pricing.
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better

Navigation

PricingSpeedLatencyEnd-to-End Response TimeAPI FeaturesSummary Table of Key Comparison Metrics

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: Input and Output Prices

USD per 1M Tokens; Lower is better
Input price
Output price

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Speed vs. Price

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens
Most attractive quadrant
Amazon
Azure
DeepInfra
Google Vertex
Kimi
Kimi Turbo
Nebius (FP8)
Novita

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).

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

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

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output Tokens per Second; Higher is better; 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 median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

Latency vs. Output Speed

Latency: Seconds to First Token Received; Output Speed: Output Tokens per Second; 10,000 Input Tokens
Most attractive quadrant
Size represents Price (USD per M Tokens)
Amazon
Azure
DeepInfra
Google Vertex
Kimi
Kimi Turbo
Nebius (FP8)
Novita

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).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

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

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to First Token Received; Lower is better; 10,000 Input Tokens
Input processing time
'Thinking' time (reasoning models, where applicable)

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.

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

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better; 10,000 Input Tokens
Input processing time
'Thinking' time (reasoning models)
Outputting 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

For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.

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

API Features

Function (Tool) Calling & JSON Mode

ModelsFunction callingJSON Mode
Kimi Turbo logoKimi Turbo
Kimi logoKimi
Google Vertex logoGoogle Vertex
Amazon logoAmazon
Nebius (FP8) logoNebius (FP8)
DeepInfra logoDeepInfra
Novita logoNovita
Azure logoAzure

Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.

Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

Context Window

Context Window: Tokens Limit; Higher is better

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

While models have their own context window, in cases this is limited by providers.

Summary Table of Key Comparison Metrics

Frequently Asked Questions

Common questions about Kimi K2 Thinking providers

Kimi K2 Thinking is available through 8 API providers: Kimi Turbo, Kimi, Google Vertex, Amazon, Nebius (FP8), DeepInfra, Novita, and Azure. Each provider offers different performance characteristics and pricing.

Kimi K2 Thinking is currently available through 8 API providers that we benchmark and track.

The fastest providers for Kimi K2 Thinking by output speed are Google Vertex (251.6 t/s), Amazon (105.4 t/s), and DeepInfra (97.0 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for Kimi K2 Thinking are Google Vertex (0.45s), DeepInfra (0.51s), and Azure (1.15s). Lower latency means faster initial response time.

The most affordable providers for Kimi K2 Thinking by blended price are DeepInfra ($0.85 per 1M tokens), Kimi ($1.07 per 1M tokens), and Google Vertex ($1.07 per 1M tokens). Blended price uses a 3:1 input to output token ratio.

The providers with the lowest input token pricing for Kimi K2 Thinking are DeepInfra ($0.47 per 1M input tokens), Kimi ($0.60 per 1M input tokens), and Google Vertex ($0.60 per 1M input tokens).

The providers with the lowest output token pricing for Kimi K2 Thinking are DeepInfra ($2.00 per 1M output tokens), Kimi ($2.50 per 1M output tokens), and Google Vertex ($2.50 per 1M output tokens).

Prices for Kimi K2 Thinking vary up to 3.4x across providers. The most affordable is DeepInfra at $0.85 per 1M tokens, while Kimi Turbo charges $2.86 per 1M tokens.

Output speed for Kimi K2 Thinking varies significantly across providers. Google Vertex is the fastest at 251.6 t/s, which is 13.6x faster than Kimi at 18.5 t/s.

7 of 8 providers support JSON mode for Kimi K2 Thinking: Kimi Turbo, Kimi, Google Vertex, Nebius (FP8), DeepInfra, Novita, and Azure.

All 8 providers of Kimi K2 Thinking support function calling (tool use).

For Kimi K2 Thinking, Google Vertex offers the best performance with highest speed and lowest latency. For cost optimization, DeepInfra provides the most competitive pricing.

When choosing a provider for Kimi K2 Thinking, 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 K2 Thinking's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview