LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Kimi K3 Fast

moonshotai·moonshotai/kimi-k3-fast·GA·Open weights·kimi-k3 series·NEW
Kimi multimodal agent model for visual understanding, coding, and planning

Kimi K3 Fast by moonshotai is offered by 5 providers on this page. Its reference price is $4.50 per 1M input tokens and $22.50 per 1M output tokens. The lowest paid channel is Neuralwatt at $3.00 / $15.00 per 1M, about 1.5× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 1,040,384 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, PDF, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Specs & pricing

Input / output per 1M tokens
Reference price·LLM Gateway
$4.50 / $22.50
Blended $9.00 · Cache read $0.45
Lowest paid·NeuralwattGateway
$3.00 / $15.00
Blended $6.00 · 1.5× spread
Context
1,040,384
Output limit
1,040,384
Knowledge cutoff
—
Released / updated
2026-07-16 / 2026-08-03
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDFVideo

Available at 5 providers5 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NeuralwattGateway$3.00$15.00$0.30—1,048,560 ⚠1,048,560
Vercel AI GatewayCloud$4.50$22.50$0.45—1,000,000 ⚠131,072
Venice AI
kimi-k3-fast-api
Gateway$4.50$22.50$0.45—1,000,000 ⚠131,072
Fireworks AICloud$4.50$22.50$0.45—1,048,576 ⚠131,072
LLM GatewayGateway$4.50$22.50$0.45—1,040,3841,040,384

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Neuralwatt$1,026.00
2Vercel AI Gateway$1,539.00
3Venice AI$1,539.00
4Fireworks AI$1,539.00
5LLM Gateway$1,539.00
The cheapest paid channel is the only channel.

Reasoning control

effort = loweffort = higheffort = maxeffort = noneToggle (on / off)effort = mediumbudget_tokens ≥ 1,024effort = xhigh

Related models

Kimi K3same series$3.00 / $15.00Kimi K3-256Ksame series$0 / $0Kimi K3 Ecosame series$1.00 / $4.00GLM-5.2cheaper alternative$1.40 / $4.40DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Procheaper alternative$0.435 / $0.87GLM-5.3-Flashcheaper alternative$0.075 / $0.25

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$22.50$02026-08-052026-08-132026-08-05 · Input list $4.502026-08-06 · Input list $4.502026-08-07 · Input list $4.502026-08-08 · Input list $4.502026-08-09 · Input list $4.502026-08-10 · Input list $4.502026-08-11 · Input list $4.502026-08-12 · Input list $4.502026-08-13 · Input list $4.502026-08-05 · Output list $22.502026-08-06 · Output list $22.502026-08-07 · Output list $22.502026-08-08 · Output list $22.502026-08-09 · Output list $22.502026-08-10 · Output list $22.502026-08-11 · Output list $22.502026-08-12 · Output list $22.502026-08-13 · Output list $22.502026-08-05 · Min blended $9.002026-08-06 · Min blended $9.002026-08-07 · Min blended $9.002026-08-08 · Min blended $9.002026-08-09 · Min blended $6.002026-08-10 · Min blended $6.002026-08-11 · Min blended $6.002026-08-12 · Min blended $6.002026-08-13 · Min blended $6.00
Data partly from models.dev (MIT) · LLM Gateway official docs ↗