Kimi K2.6 API pricing

21 providers serve Kimi K2.6. Kimi K2.6 is an open-weight model (Modified MIT) with 1059B total parameters, 32B active per token (mixture-of-experts), up to 262K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-11-22 · list prices from provider APIs
Input floor $0.380/1M at Clf AI Gateway Output floor $1.60/1M at Clf AI Gateway Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Clf AI Gateway $0.380 $1.60output floor $0.064 262K
Kyma $0.591 $2.76 - 262K
W&B Inference $0.650 $3.41 $0.150 262K Use
OpenRouter marketplace quote $0.650 $3.41 $0.150 262K Use
DeepInfra $0.750 $3.50 $0.150 262K Use
Novita AI $0.800 $3.40 $0.160 262K Use
GMI Cloud $0.855 $3.60 $0.144 262K Use
Empiriolabs $0.894 $3.71 $0.179 262K
Azure AI Foundry $0.950 $4.00 $0.160 262K Use
Cloudflare $0.950 $4.00 $0.160 262K Use
Fireworks AI $0.950 $4.00 $0.160 262K Use
Moonshot $0.950 $4.00 $0.160 262K Use
Nebius $0.950 $4.00 $0.160 262K Use
Streamlake $0.950 $4.00 $0.160 262K
Aihubmix $0.950 $4.00 $0.161 262K
Baseten $0.950 $4.00 $0.160 262K Use
Replicate $0.950 $4.00 - - Use
Tensormesh $0.960 $4.00 - 33K
Inferenceapis $0.980 $4.55 - 262K
Sail $1.00 $4.00 $0.200 262K
Together AI $1.20 $4.50 $0.200 262K Use

The cheapest way to run Kimi K2.6

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $74.60/month, at Clf AI Gateway. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. On output-token cost alone, the API floor remains below our self-hosting estimate of ~$1.76/1M. Details below. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Or run it yourself: Kimi K2.6 self-hosting economics

Kimi K2.6 is open-weight (Modified MIT), so the API price above competes with the GPU-hour market. 1059B total parameters (MoE, ~32B active per token) needs roughly 1457 GB VRAM at FP8 or 729 GB at INT4, KV-cache headroom included.

No single GPU fits Kimi K2.6 at FP8 (1457 GB needed), so it needs a multi-GPU node. Cheapest tracked option: 8× MI300X (192 GB each) at roughly $4.00/hr total (RunPod). Rent 8× MI300X at RunPod → INT4 quantization drops the requirement to 729 GB. Tune it in the calculator.
Breakeven estimate: a well-batched vLLM deployment on 8× MI300X ($4.00/hr) at ~1265 aggregate tok/s and 50% utilization works out to roughly $1.76 per 1M output tokens, versus $1.60 via the cheapest output-token API (Clf AI Gateway). The API is cheaper unless your utilization or throughput beats these assumptions. Planning estimate: throughput varies with hardware, quantization, batch size and context. Tune it in the calculator.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Kimi K2.7 Code $0.380 $1.60 23
Kimi K3 $0.192 $12.50 21
Kimi K3.1 Pro $0.240 $8.40 13
Kimi K2.5 $0.450 $2.25 11
Kimi K2 Thinking $0.600 $1.20 10
Kimi K2 $0.500 $2.00 10

FAQ

What is the cheapest API for Kimi K2.6?

As of 2026-11-22, the lowest input price for Kimi K2.6 is Clf AI Gateway at $0.380 per 1M input tokens. The lowest output price is Clf AI Gateway at $1.60 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Kyma at $0.591, a 55% difference.

How much VRAM do you need to self-host Kimi K2.6?

Kimi K2.6 has 1059B parameters, so plan for roughly 1457 GB of VRAM at FP8 or 729 GB at INT4/AWQ, KV-cache headroom included. That exceeds a single GPU. A typical node is 8× MI300X.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON