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 Results for other workloads are historical and no longer updated.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).
This analysis is intended to support you in choosing the best API provider of Kimi K2.6 for your use-case.
Fastest
Azure
Nebius
CoreWeave
Baseten
ParasailOutput speed
Total 13 providers
Lowest Latency
AzureNebiusCoreWeaveBasetenParasailTime to first answer token
Total 13 providers
Lowest Price
CoreWeave
SiliconFlow (FP8)
DeepInfra (FP4)
NovitaParasailBlended 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 Azure (216.6 t/s), Nebius (206.2 t/s), and CoreWeave (172.7 t/s). Speed varies significantly across providers, with a 686% difference between the fastest and slowest.
- For latency, Azure (22.07s), Nebius (23.61s), and CoreWeave (27.11s) offer the lowest time to first answer token.
- For pricing, CoreWeave (0.58), SiliconFlow (FP8) (0.59), and DeepInfra (FP4) (0.60) offer the lowest blended prices per 1M tokens. Prices vary up to 2.2x across providers.
- Azure offers the best performance with both the highest speed and lowest latency. For cost optimization, CoreWeave provides the most competitive pricing.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Kimi K2.6
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
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
Key Comparison Metrics & API Features
| Baseten | 262k | Open | -- | 161 | 0.64 | 31.39 | 27.64 | ||
 Crusoe | 262k | Open | -- | -- | -- | -- | -- | ||
| CoreWeave | 262k | Open | -- | 185 | 1.17 | 27.88 | 24.01 | ||
| Novita | 262k | Open | -- | 60 | 1.94 | 84.76 | 74.45 | ||
 GMI | 262k | Open | -- | -- | -- | -- | -- | ||
 Fireworks | 262k | Open | -- | 69 | 0.79 | 72.26 | 64.25 | ||
| SiliconFlow | 262k | Open | -- | 33 | 1.34 | 149.84 | 133.50 | ||
| DeepInfra | 262k | Open | -- | 23 | 1.26 | 215.64 | 192.73 | ||
| Parasail | 262k | Open | -- | 144 | 1.26 | 35.55 | 30.83 | ||
| Nebius | 262k | Open | -- | 206 | 2.03 | 26.04 | 21.59 | ||
 Cloudflare | 262k | Open | -- | -- | -- | -- | -- | ||
| Microsoft Azure | 262k | Open | -- | 216 | 1.40 | 24.30 | 20.58 | ||
 Kimi | 256k | Open | -- | 44 | 2.99 | 114.53 | 100.27 | ||
Frequently Asked Questions
Common questions about Kimi K2.6 providers
Kimi K2.6 is available through 13 API providers: Baseten, 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 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).
Output speed for Kimi K2.6 varies significantly across providers. Azure is the fastest at 216.6 t/s, which is 7.9x faster than DeepInfra (FP4) at 27.6 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).
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