This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Kimi has launched a newer model, Kimi K3 (max). We suggest considering it instead.

For more information, see comparison of Kimi K3 (max) to other models and API provider benchmarks for Kimi K3 (max).

Kimi K2.6 logo
Kimi
•

Open weights model

•

Released April 2026

Kimi K2.6 API Provider Benchmarking & Analysis

Model Comparison

Analysis of API providers for Kimi K2.6 across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Clarifai, Crusoe (NVFP4), CoreWeave, Novita, GMI FP8, Fireworks, SiliconFlow (FP8), DeepInfra (FP4), Parasail, Nebius, Cloudflare, Microsoft Azure, Kimi.

Fastest

#1
CoreWeaveCoreWeave
257.4 t/s
#2
NebiusNebius
254.3 t/s
#3
AzureAzure
180.1 t/s
#4
ParasailParasail
121.6 t/s
#5
FireworksFireworks
83.9 t/s

Output speed

Total 13 providers

Lowest Latency

#1
CoreWeaveCoreWeave
18.45 s
#2
NebiusNebius
19.43 s
#3
AzureAzure
26.18 s
#4
ParasailParasail
38.01 s
#5
FireworksFireworks
54.12 s

Time to first answer token

Total 13 providers

Lowest Price

#1
CoreWeaveCoreWeave
$0.58
#2
SiliconFlow (FP8)SiliconFlow (FP8)
$0.59
#3
DeepInfra (FP4)DeepInfra (FP4)
$0.60
#4
NovitaNovita
$0.61
#5
GMI FP8GMI FP8
$0.63

Blended price (per 1M tokens)

Total 13 providers

Kimi K2.6 is available through 13 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 CoreWeave (257.4 t/s), Nebius (254.3 t/s), Azure (180.1 t/s). Speed varies significantly across providers, with a 604% difference between the fastest and slowest.
  • For latency, CoreWeave (18.45s), Nebius (19.43s), Azure (26.18s) offer the lowest time to first answer token.
  • For pricing, CoreWeave (0.58), SiliconFlow (FP8) (0.59), DeepInfra (FP4) (0.60) offer the lowest blended prices per 1M tokens. Prices vary up to 2.2x across providers.
  • CoreWeave stands out as the overall leader, ranking first across all three categories: speed, latency, and pricing.

Highlights

Speed

Output tokens per second · Higher is better

End-to-End Response Time

Seconds · Lower is better

Price

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

Pricing

Pricing: Cache Hit, Input, and Output

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.

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Reduction in input token cost due to cache hit relative to input price. Formula: 1 - (Cache Hit Price per Token / Input Token Price), where cache hit price is the first-party cache hit price or the median provider cache hit price. Note that this discount figure does not account for all costs associated with cache hits, such as cache write and storage costs.

Output Speed vs. Price

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

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 K2.6

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).

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
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).

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

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

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

Clarifai logoClarifai
262k
Open
$0.76
--
--
--
--
Crusoe logoCrusoe
262k
Open
$0.38
--
--
--
--
CoreWeave logoCoreWeave
262k
Open
--
257
1.16
20.40
17.29
Novita logoNovita
262k
Open
$0.33
47
1.95
108.36
95.66
GMI logoGMI
262k
Open
--
--
--
--
--
Fireworks logoFireworks
262k
Open
$0.30
84
1.08
60.08
53.04
SiliconFlow logoSiliconFlow
262k
Open
$0.32
37
1.85
137.20
121.68
DeepInfra logoDeepInfra
262k
Open
$0.27
52
0.88
95.57
85.12
Parasail logoParasail
262k
Open
$0.31
122
1.40
42.12
36.61
Nebius logoNebius
262k
Open
$0.76
254
1.93
21.39
17.50
Cloudflare logoCloudflare
262k
Open
$0.30
43
1.22
116.01
103.20
Microsoft Azure logoMicrosoft Azure
262k
Open
$0.76
180
1.46
28.96
24.72
Kimi logoKimi
256k
Open
$0.36
39
3.09
130.53
114.57

Frequently Asked Questions

Common questions about Kimi K2.6 providers

Kimi K2.6 is available through 13 API providers: Clarifai, Crusoe (NVFP4), CoreWeave, Novita, GMI FP8, Fireworks, SiliconFlow (FP8), DeepInfra (FP4), Parasail, Nebius, Cloudflare, Azure, and Kimi. Each provider offers different performance characteristics and pricing.

Kimi K2.6 is currently available through 13 API providers that we benchmark and track.

The fastest providers for Kimi K2.6 by output speed are CoreWeave (257.4 t/s), Nebius (254.3 t/s), and Azure (180.1 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 K2.6 are CoreWeave (18.45s), Nebius (19.43s), and Azure (26.18s). Lower latency means faster initial response time.

The most affordable providers for Kimi K2.6 by blended price are CoreWeave ($0.58 per 1M tokens), SiliconFlow (FP8) ($0.59 per 1M tokens), and DeepInfra (FP4) ($0.60 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 K2.6 are CoreWeave ($0.65 per 1M input tokens), Crusoe (NVFP4) ($0.70 per 1M input tokens), and DeepInfra (FP4) ($0.75 per 1M input tokens).

The providers with the lowest output token pricing for Kimi K2.6 are Novita ($3.40 per 1M output tokens), SiliconFlow (FP8) ($3.40 per 1M output tokens), and CoreWeave ($3.41 per 1M output tokens).

Prices for Kimi K2.6 vary up to 2.2x across providers. The most affordable is CoreWeave at $0.58 per 1M tokens, while Clarifai charges $1.25 per 1M tokens.

Output speed for Kimi K2.6 varies significantly across providers. CoreWeave is the fastest at 257.4 t/s, which is 7.0x faster than SiliconFlow (FP8) at 36.6 t/s.

All 13 providers of Kimi K2.6 support JSON mode for structured output.

All 13 providers of Kimi K2.6 support function calling (tool use).

CoreWeave leads across all key metrics for Kimi K2.6, offering the fastest speed, lowest latency, and most competitive pricing.

When choosing a provider for Kimi K2.6, 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 K2.6's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview