The AI arena is free today

Open Superagent
API Provider2 active models1 organization

Moonshot AI: API pricing, speed & models

Moonshot AI hosts 2 active AI models, with input pricing from $0.95 per 1M tokens, with median throughput of 79 characters/sec, and P95 time to first token of 30.55s, with 90.9% success rate over 7 days. Compare Moonshot AI's API speed, pricing, and reliability against other inference providers.

First-party only
Median throughput79 c/s
Median TTFT3.47s
P95 TTFT30.55s
Success rate (7d)90.9%
From$0.95 /M tok

Catalog

Type
Price
9 models
Model
Kimi K3cache pricing
Kimi K3cache pricing
Kimi K3cache pricing
Kimi K2.6cache pricing
Kimi K2.6cache pricing
Kimi K2.6cache pricing
At a glance

Moonshot AIpricing, performance & catalog

The citable facts about Moonshot AI's 3 models — sourced from provider APIs and refreshed continuously.

Lowest price
Kimi K2.6 at $0.950 per 1M input tokens
Highest median throughput
Kimi K3 at 79 chars/s
Lowest median TTFT
Kimi K3 at 3.47s
Largest context
Kimi K3 at 1.0M tokens
Catalog
2 active models from 1 organization

Fastest median throughput

  1. 1Kimi K379 c/s

FAQ

Common questions about Moonshot AI.

What is Moonshot AI?

Moonshot AI is an API provider that hosts large language models. Active models: 2; From (input): $0.95 / 1M tok; Median throughput: 79 c/s; Median TTFT: 3.47s; Success rate (7d): 90.9%.

How many models does Moonshot AI offer?

Moonshot AI currently serves 2 active models out of 4 historical offerings on LLM Stats.

What is Moonshot AI's API pricing?

Moonshot AI input pricing starts from $0.95 per 1M tokens, with the most expensive offering at $3 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

How fast is Moonshot AI?

Moonshot AI delivers a median throughput of 79 characters per second and P95 time to first token of 30.55s across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is Moonshot AI reliable?

Moonshot AI has a 90.9% success rate across 11 API calls in the last 7 days, with a 9.1% error rate.

Does Moonshot AI support function calling?

Yes. 6 of 2 models on Moonshot AI support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does Moonshot AI support JSON mode and structured output?

Yes. 6 of 2 models on Moonshot AI support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Does Moonshot AI offer batch inference?

Yes. 3 of 2 models on Moonshot AI support batch inference for cheaper, asynchronous workloads.

Does Moonshot AI support multimodal models?

Yes. Moonshot AI's catalog includes 2 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Whose models does Moonshot AI host?

Moonshot AI hosts models from Moonshot AI. See the Models tab for the full catalog grouped by creator.

How do I start using Moonshot AI?

Sign up at https://www.moonshot.ai/ to get an API key, then call Moonshot AI's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at Moonshot AI's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.