Which is cheaper, Kimi K3 and GPT-6 Luna?

GPT-6 Luna has the lowest input price. Per 1M input tokens: Kimi K3 from $2.70 and GPT-6 Luna from $0.10.

Which has the larger context window, Kimi K3 and GPT-6 Luna?

Kimi K3 has the largest context window: Kimi K3 1,048,576 tokens and GPT-6 Luna 400,000 tokens.

Which is smarter, Kimi K3 and GPT-6 Luna?

Kimi K3 scores highest on the Artificial Analysis Intelligence Index: Kimi K3 43.6 and GPT-6 Luna 38.1.

Can I switch between Kimi K3 and GPT-6 Luna without changing my code?

Yes. All of them are served through FastRouter's OpenAI-compatible API, so switching is a change of the model parameter (moonshotai/kimi-k3, openai/gpt-6-luna).

Kimi K3 vs GPT-6 Luna

Side-by-side pricing per provider, context window, benchmark scores and speed, all on one OpenAI-compatible API.

Kimi K3 MoonshotAImoonshotai/kimi-k3

GPT-6 Luna OpenAIopenai/gpt-6-luna

Creator

MoonshotAI

OpenAI

Released

Jul 16, 2026

Sep 22, 2026

Context window

1.05M

400K

Max output

1.05M

128K

Input / 1MLowest provider price

$2.70$2.70–$3.00 across 4

$0.10

Output / 1MLowest provider price

$13.50$13.50–$15.00 across 4

$0.50

Providers

IntelligenceArtificial Analysis index

43.6

38.1

CodingArtificial Analysis index

76.2

—

LatencyMedian time to first token

7.4s

—

ThroughputMedian tokens per second

<1 t/s

—

Accepts

Text, Image

Files, Image, Text

Produces

Text

Tool calling

Yes

Structured output

Yes

Reasoning

Yes

Kimi K3 vs GPT-6 Luna: summary

Kimi K3 and GPT-6 Luna are both available through FastRouter's OpenAI-compatible API, so switching between them is a change of model id, not a new integration.

Kimi K3, from MoonshotAI, has a 1,048,576-token context window, costs from $2.70/1M input and $13.50/1M output tokens across 4 providers and scores 43.6 on the Artificial Analysis Intelligence Index.

GPT-6 Luna, from OpenAI, has a 400,000-token context window, costs $0.10/1M input and $0.50/1M output tokens and scores 38.1 on the Artificial Analysis Intelligence Index.

GPT-6 Luna is the cheapest on input, 27× cheaper than the next model, Kimi K3 has the largest context window and Kimi K3 scores highest for intelligence.

Switch with one line

client = OpenAI(base_url="https://api.fastrouter.ai/api/v1", api_key="<FASTROUTER_API_KEY>") client.chat.completions.create(model="moonshotai/kimi-k3", messages=[...]) # or client.chat.completions.create(model="openai/gpt-6-luna", messages=[...])

Full API docs

Frequently asked questions

More comparisons

Benchmark scores sourced from ArtificialAnalysis