NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM

Cheapest Kimi API: below Moonshot AI on 4 of 4 models (November 2026)

Updated November 20, 2026, 09:00 UTC. UberLLM prices are read live when the page is built (every hour); other providers' prices were checked November 19, 2026 or read from their public price lists at build. UberLLM wrote this page and is one of the providers in it.

On November 20, 2026, UberLLM was below Moonshot AI’s own price on both input and output for 4 of the 4 Kimi models we compared, with UberLLM’s card fee added. Among the real-time prices in the table, UberLLM was lowest on 7 of the 7 models. Moonshot’s Batch API charges 60% of its price on Kimi K3.1 Pro and K3 for jobs that can wait, and is still above UberLLM on every model here. UberLLM prices are the best seller’s price now; they move during the day.

Some UberLLM prices here are more than 70% below list. They are what buyers were billed, not errors. Why so cheap?

ProviderHow you payPrice against Moonshot AI’s
UberLLMPer token, prepaid; 5.5% + $0.50 card fee when adding creditBelow it on 4 of 4 models (card fee added)
Kimi API (Moonshot AI)Per token, direct from Moonshot AIThe list price
OpenRouterPrepaid credit; 5.5% when buying creditAgainst Moonshot AI’s price: lower on 3, higher on 1 of 4
Vercel AI GatewayCredit in your Vercel accountAgainst Moonshot AI’s price: the same on 4 of 4
RequestyPrepaid; 5% on model costs, added when you top upAgainst Moonshot AI’s price: the same on 2, lower on 2 of 4
DeepInfraRuns models on its own GPUs, per tokenAgainst Moonshot AI’s price: the same on 1, lower on 3 of 4
Novita AIRuns open models on its own GPUs, per tokenAgainst Moonshot AI’s price: the same on 3, lower on 1 of 4

UberLLM first, then Moonshot AI’s own API, then the other providers that list these models. The table below shows, model by model, who is lowest. An empty cell means we could not confirm it on the provider's own pages.

Kimi prices, model by model ($ per 1M input / output tokens)

ModelUberLLMMoonshot AIMoonshot AI BatchOpenRouterVercel AI GatewayRequestyDeepInfraNovita AI
Kimi K3Why so cheap?$0.0384 / $0.2021$3.00 / $15.00$1.80 / $9.00$0.192 / $16.00$3.00 / $15.00$3.00 / $15.00$2.85 / $14.25$3.00 / $15.00
Kimi K3.1 ProWhy so cheap?$0.2054 / $1.027$2.00 / $10.00$1.20 / $6.00$0.253 / $8.80$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00
Kimi K2.7 CodeWhy so cheap?$0.0158 / $0.0739$0.95 / $4.00$0.60 / $3.00$0.95 / $4.00$0.75 / $3.50$0.68 / $3.40$0.95 / $4.00
Kimi K2.5$0.00289 / $0.0144$0.50 / $2.50$0.60 / $3.00$0.45 / $2.25$0.45 / $2.25$0.60 / $3.00
Kimi K2 Thinking$0.00594 / $0.0248$0.60 / $2.50$0.47 / $2.00$0.60 / $2.50
Kimi K2.6Why so cheap?$0.0235 / $0.1081$0.95 / $4.00$0.65 / $3.41$0.95 / $4.00$0.75 / $3.50$0.75 / $3.50$0.80 / $3.40
Kimi K2$0.398 / $1.606$0.57 / $2.30$0.57 / $2.30

UberLLM: the best seller’s price, read November 20, 2026; the 5.5% card fee is not in the cell. Moonshot AI: its own pricing page, checked November 19, 2026; an empty cell means its page does not list that model. Moonshot AI Batch: 60% of its standard price, as its page states. OpenRouter, Vercel AI Gateway, Requesty, DeepInfra and Novita AI: each one’s public model list, read when this page was built.

Each provider, good and bad

UberLLM

Pick it if: You want Kimi below Moonshot AI’s price, billed per request with no plan, and the same key for every other model.

Watch for: Requests go to third-party providers, not to Moonshot AI directly: if you need Moonshot AI’s own data terms, use its API. The price is a market price and can be higher when the lower-priced sellers are busy (cap it with provider.max_price).

Source: UberLLM Kimi prices (live, November 20, 2026)

Kimi API (Moonshot AI)

Pick it if: You want Moonshot’s own service, its context caching and Batch on K3 models.

Watch for: K2 models are closed to new accounts since October 31, 2026 and Moonshot plans to retire them by the end of December 2026.

Source: Moonshot AI pricing (checked 2026-11-19)

OpenRouter

Pick it if: You already use OpenRouter for other models and want automatic failover.

Watch for: Its 5.5% credit fee comes on top of the prices in the table.

Source: OpenRouter pricing, its model list (checked 2026-11-19)

Vercel AI Gateway

Pick it if: Your app runs on Vercel or uses the AI SDK.

Watch for: No markup on provider token prices, so no saving per token either.

Source: Vercel AI Gateway pricing, its model list (checked 2026-11-19)

Requesty

Pick it if: You want routing rules, fallbacks and per-team spend limits.

Watch for: The 5% top-up fee comes on top of the prices in the table.

Source: Requesty pricing, its model list (checked 2026-11-19)

DeepInfra

Pick it if: Steady prices on US hosting for open models.

Watch for: Not every version is listed.

Source: DeepInfra pricing, its model list (checked 2026-11-19)

Novita AI

Pick it if: Low prices on open models.

Watch for: Check that your version is listed.

Source: Novita pricing, its model list (checked 2026-11-19)

How to switch to UberLLM

UberLLM takes OpenAI-style requests: change the base URL, the key and the model id (Kimi ids on UberLLM start with moonshotai/).

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uberllm.dev/v1",  # was: https://api.moonshot.ai/v1
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="moonshotai/kimi-k3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Questions

Can I still use Kimi K2 models?

Moonshot stopped offering K2 models to newly registered users on October 31, 2026 and plans to retire them by the end of December 2026. On UberLLM a K2 model is sold while a seller offers it; the table shows which ones have a price today.

Does Kimi have a batch discount?

Yes. Moonshot bills Batch API requests at 60% of the standard price, for Kimi K3.1 Pro and Kimi K3.

Can I cap what a Kimi request costs on UberLLM?

Yes. Send provider.max_price with the most you will pay per million tokens; the request only goes to sellers at or under it.

Are there other fees on UberLLM?

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.