Moonshot AI Kimi · LLM API pricing

Kimi K3 API pricing: cheapest provider

9 providers sell Kimi K3. SiliconFlow is cheapest; the most expensive charges 1.1× as much for the same model.

Cheapest$5.40per 1M · SiliconFlow
Input · output$2.70 / $13.50per 1M tokens
Price gap1.1×across 9 providers
Accuracy93.1%GPQA · max reasoning
Context1Mmax tokens

$5.40 SiliconFlow1.1× spread$6.00 Nebius Token Factory

Compare all 9 providers ⇄ Compare with another model

Already paying for Kimi K3? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Oct 15, 2026 · How we collect and rank prices

Ranked for your volume

Kimi K3 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 SiliconFlowInference provider - lowest for your volumePricing page	$54.00	$2.70	$13.50	$0.27	1,048,576
2 DeepInfraInference providerPricing page	$57.00	$2.85	$14.25	$0.285	1,048,576
3 Alibaba Cloud Model StudioAI platformSingapore (International) list price; other regions differ.Pricing page	$60.00	$3.00	$15.00	$0.30	1,048,576
4 BasetenInference providerPricing page	$60.00	$3.00	$15.00	$0.30	1,048,576
5 Fireworks AIInference providerPricing page	$60.00	$3.00	$15.00	$0.30	1,048,576
6 Moonshot AIModel developerPricing page	$60.00	$3.00	$15.00	$0.30	1,048,576
7 Nebius Token FactoryCloud platformPricing page	$60.00	$3.00	$15.00	Not listed	1,024,000
8 Novita AIInference providerPricing page	$60.00	$3.00	$15.00	$0.30	1,048,576
9 Together AIInference providerPricing page	$60.00	$3.00	$15.00	$0.30	1,048,576

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 K3 provider | Input / 1M tokens | Output / 1M tokens | 10M in + 2M out per month |
|---|---:|---:|---:|
| SiliconFlow | $2.70 | $13.50 | $54.00 |
| DeepInfra | $2.85 | $14.25 | $57.00 |
| Alibaba Cloud Model Studio | $3.00 | $15.00 | $60.00 |
| Baseten | $3.00 | $15.00 | $60.00 |
| Fireworks AI | $3.00 | $15.00 | $60.00 |
| Moonshot AI | $3.00 | $15.00 | $60.00 |
| Nebius Token Factory | $3.00 | $15.00 | $60.00 |
| Novita AI | $3.00 | $15.00 | $60.00 |
| Together AI | $3.00 | $15.00 | $60.00 |

Standard list prices as of Oct 31, 2026. Source: [AISelect.online](https://aiselect.online/models/kimi-k3)

Accuracy: GPQA Diamond (graduate-level science questions) measured by Epoch AI (CC BY 4.0) on kimi-k3_max, run Jul 16, 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: $5.40 per 1M tokens at SiliconFlow. All price changes

Switch to the cheapest provider

Switch to SiliconFlow

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.siliconflow.com/v1",
    api_key=os.environ["SILICONFLOW_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/Kimi-K3",
    messages=[{"role": "user", "content": "Hello"}],
)

Base URL from SiliconFlow's API docs, model name from the open pricing datasets. Check the model page in SiliconFlow's docs before you switch production traffic.

Compare Kimi K3 with another model

Kimi K3 vs Claude Sonnet 5.5 Kimi K3 vs DeepSeek V4 Pro Kimi K3 vs GLM-5.3 Kimi K3 vs MiniMax-M3

Or pick any model

Model A

Model B

Before you pick a provider

SiliconFlow lists Kimi K3 10% 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 1M to 1M tokens. A cheaper host may not accept your longest prompts.

8 of 9 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 K2.6, 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 K3 prices (RSS) - Methodology