Moonshot AI Kimi · LLM API pricing

Kimi K2.6 API pricing: cheapest provider

8 providers sell Kimi K2.6. W&B Inference (CoreWeave) is cheapest; the most expensive charges 1.3× as much for the same model.

Cheapest$1.34per 1M · W&B Inference (CoreWeave)
Input · output$0.65 / $3.41per 1M tokens
Price gap1.3×across 8 providers
Accuracy90.8%GPQA
Context262Kmax tokens

$1.34 W&B Inference (CoreWeave)1.3× spread$1.71 Nebius Token Factory

Compare all 8 providers ⇄ Compare with another model

Already paying for Kimi K2.6? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Sep 28, 2026 · How we collect and rank prices

Ranked for your volume

Kimi K2.6 monthly cost by provider

Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.

Input tokens per month (millions)Prompts, context and documents you send.Output tokens per month (millions)Tokens the model generates.

More requirements: caching, context, features, provider

Cached share of input (%)0 = no caching. Only documented cache-read rates qualify.Required context per request (tokens)0 = any. Providers without a sufficient known limit are excluded.Required featureProvider requirement

Provider	Estimated / month	Input / 1M	Output / 1M	Cached input / 1M	Context
1 W&B Inference (CoreWeave)Inference provider - lowest for your volumePricing page	$13.32	$0.65	$3.41	$0.15	262,000
2 DeepInfraInference providerPricing page	$14.50	$0.75	$3.50	$0.15	262,144
3 SiliconFlowInference providerPricing page	$14.50	$0.77	$3.40	$0.14	262,000
4 Novita AIInference providerPricing page	$14.80	$0.80	$3.40	$0.16	262,144
5 Cloudflare Workers AICloud platformPricing page	$17.50	$0.95	$4.00	$0.16	262,144
6 Microsoft Azure AI FoundryCloud platformPricing page	$17.50	$0.95	$4.00	$0.16	262,144
7 Moonshot AIModel developerPricing page	$17.50	$0.95	$4.00	$0.16	262,144
8 Nebius Token FactoryCloud platformPricing page	$17.50	$0.95	$4.00	Not listed	262,144

Order depends on listed price for your volume only. No provider pays for its position.

Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.

Share this comparison as a Markdown table

For a post, a doc or a forum answer. The source line links back here, so readers can check today's prices.

Markdown

| Kimi K2.6 provider | Input / 1M tokens | Output / 1M tokens | 10M in + 2M out per month |
|---|---:|---:|---:|
| W&B Inference (CoreWeave) | $0.65 | $3.41 | $13.32 |
| DeepInfra | $0.75 | $3.50 | $14.50 |
| SiliconFlow | $0.77 | $3.40 | $14.50 |
| Novita AI | $0.80 | $3.40 | $14.80 |
| Cloudflare Workers AI | $0.95 | $4.00 | $17.50 |
| Microsoft Azure AI Foundry | $0.95 | $4.00 | $17.50 |
| Moonshot AI | $0.95 | $4.00 | $17.50 |
| Nebius Token Factory | $0.95 | $4.00 | $17.50 |

Standard list prices as of Oct 31, 2026. Source: [AISelect.online](https://aiselect.online/models/kimi-k2-6)

Accuracy: GPQA Diamond (graduate-level science questions) measured by Epoch AI (CC BY 4.0) on kimi-k2.6, run May 1, 2026. The model is the same at every provider, though quantized deployments can score lower.

Price history

The cheapest price has not changed since tracking started on Sep 28, 2026: $1.34 per 1M tokens at W&B Inference (CoreWeave). All price changes

Switch to the cheapest provider

Switch to W&B Inference (CoreWeave)

Already using the OpenAI SDK? Change the base URL, key and model name:

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.inference.wandb.ai/v1",
    api_key=os.environ["WANDB_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2.6",
    messages=[{"role": "user", "content": "Hello"}],
)

Base URL from W&B Inference (CoreWeave)'s API docs, model name from the open pricing datasets. Check the model page in W&B Inference (CoreWeave)'s docs before you switch production traffic.

Compare Kimi K2.6 with another model

Or pick any model

Model A

Model B

Before you pick a provider

W&B Inference (CoreWeave) lists Kimi K2.6 22% below the developer's own API (Moonshot AI) on a blended basis. Check rate limits, data retention and model quantization before switching.

Context windows differ by provider, from 262K to 262K tokens. A cheaper host may not accept your longest prompts.

7 of 8 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.

Keep comparing

More Moonshot AI Kimi models

Kimi K3, Kimi K2.7 Code, Kimi K2.5, Kimi K2 Instruct, Kimi K2 Thinking, Kimi K3.1 Pro, Kimi K3.1 Pro Highspeed, kimi-k2-instruct-0905

All Moonshot AI Kimi API prices - All LLM API prices - Watch Kimi K2.6 prices (RSS) - Methodology