Moonshot

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by Moonshot

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Kimi K2.6 moonshotai/kimi-k2.6:moonshot	256k	$0.546/M	$2.72/M	Supported	2.5s	65.5 tps
Kimi K2.6 Thinking moonshotai/kimi-k2.6:thinking:moonshot	256k	$0.546/M	$2.72/M	Supported	2.5s	65.5 tps
Kimi K3 moonshotai/kimi-k3:moonshot	1.0M	$3.15/M	$15.75/M	$0.315/M	5s	29 tps

Kimi K2.6

moonshotai/kimi-k2.6:moonshot

Context

256k

Input /M

$0.546/M

Output /M

$2.72/M

Cache read /M

Supported

TTFT

2.5s

Throughput

65.5 tps

Kimi K2.6 Thinking

moonshotai/kimi-k2.6:thinking:moonshot

Context

256k

Input /M

$0.546/M

Output /M

$2.72/M

Cache read /M

Supported

TTFT

2.5s

Throughput

65.5 tps

Kimi K3

moonshotai/kimi-k3:moonshot

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.315/M

TTFT

5s

Throughput

29 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Moonshot via the API

Call a model served by Moonshot using its displayed model ID, including the provider suffix when selection is supported.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2.6:moonshot",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :moonshot to the model ID, set "provider": "moonshot" in the request body, or send an X-Provider: moonshot header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.