API pricing

Moonshot Pricing

Moonshot charges between $2.00 and $15.00 per 1 million output tokens, depending on the model. Kimi Latest 8K is the cheapest at $2.00/1M output and $0.200/1M input; Kimi K3 is the most expensive at $15.00/1M output. The largest context window is 1.0M tokens (Kimi K3). Prices are USD, current as of July 20, 2026.

Last updated · synced weekly from the upstream model catalog

Cheapest input

$0.200/1M

Kimi Latest 8K

Cheapest output

$2.00/1M

Kimi Latest 8K

Longest context

1.0M

Kimi K3

Models priced

28

Avg $4.46/1M output

Pricing by model

All prices in USD per 1 million tokens. All 28 priced models, cheapest first.

ModelInput / 1MOutput / 1MContext
Kimi Latest 8K$0.200$2.008K
Moonshot V1 8K$0.200$2.008K
Moonshot V1 8K 0430$0.200$2.008K
Moonshot V1 8K Vision Preview$0.200$2.008K
Kimi K2 0711
ToolsCache
$0.600$2.50131K
Kimi K2 0711 Preview$0.600$2.50131K
Kimi K2 0905
ToolsCache
$0.600$2.50262K
Kimi K2 0905 Preview$0.600$2.50262K
Kimi K2 Thinking
ReasoningToolsCache
$0.600$2.50262K
Kimi Thinking Preview$0.600$2.50131K
Kimi K2.5
VisionReasoningToolsCache
$0.600$3.00262K
Kimi Latest 32K$1.00$3.0033K
Moonshot V1 32K$1.00$3.0033K
Moonshot V1 32K 0430$1.00$3.0033K
Moonshot V1 32K Vision Preview$1.00$3.0033K
Kimi K2.6
VisionReasoningToolsCache
$0.950$4.00262K
Kimi K2.7 Code
VisionReasoningToolsCache
$0.950$4.00262K
Kimi Latest$2.00$5.00131K
Kimi Latest 128K$2.00$5.00131K
Moonshot V1 128K$2.00$5.00131K
Moonshot V1 128K 0430$2.00$5.00131K
Moonshot V1 128K Vision Preview$2.00$5.00131K
Moonshot V1 Auto$2.00$5.00131K
Kimi K2 Thinking Turbo
ReasoningToolsCache
$1.15$8.00262K
Kimi K2 Turbo Preview$1.15$8.00262K
Kimi K2.7 Code HighSpeed
VisionReasoningToolsCache
$1.90$8.00262K
Kimi K2 Turbo
ToolsCache
$2.40$10.00262K
Kimi K3
VisionReasoningToolsCache
$3.00$15.001.0M

Frequently asked questions

How much does Moonshot cost per 1M tokens?

Moonshot pricing ranges from $2.00 to $15.00 per 1 million output tokens across 28 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.

What is the cheapest Moonshot model?

Kimi Latest 8K is the cheapest Moonshot model on both axes — $0.200 per 1M input tokens and $2.00 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.

What is the largest Moonshot context window?

Kimi K3 has the largest context window in the Moonshot catalog at 1.0M input tokens, with up to 131K output tokens per response.

Does Moonshot support prompt caching?

Yes. Kimi K2.5 reads cached input at $0.100 per 1M tokens, against $0.600 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.

Which Moonshot models support reasoning or vision?

The Moonshot catalog includes 7 reasoning models, 5 vision models, 10 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.

How do I calculate my actual Moonshot bill?

Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.

Other providers

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator