OpenAI compatible API · Attested · Public status

MoonshotAI: Kimi K2.6 vs Nemotron-3-Super-120B

MoonshotAI: Kimi K2.6 vs Nemotron-3-Super-120B: compare current API pricing, context, provider routes, privacy, p50 latency, and OpenAI-compatible access.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Compare routesProviders, price, context, and policy posture in one view.

Use auto when uptime mattersKeep a primary model and let fallback handle provider failures.

Same API shapeUse the OpenAI client and set the model you want.

Practical read

Monthly evidence

Nemotron-3-Super-120B has the lower cheapest prompt+completion route on TrustedRouter. MoonshotAI: Kimi K2.6 has more provider fallback routes, while Nemotron-3-Super-120B has the larger context window. Current TrustedRouter probes show MoonshotAI: Kimi K2.6 with the lower p50 TTFT.

$4.1989/1MMoonshotAI: Kimi K2.6 cheapest route

$1.00225/1MNemotron-3-Super-120B cheapest route

1110 msMoonshotAI: Kimi K2.6 fastest measured p50 TTFT via telnyx

1155 msNemotron-3-Super-120B fastest measured p50 TTFT via digitalocean

Prices and live route measurements can change. Use the monthly reports when you need a stable evidence window, then run a small task-specific eval before choosing a production default.

MoonshotAI: Kimi K2.6Nemotron-3-Super-120B

Model idmoonshotai/kimi-k2.6nvidia/nemotron-3-super-120b

Publisher Kimi DigitalOcean Gradient AI

AI IQ IQ 119#24 —

Context262,144 tokens1,000,000 tokens

Provider routes322

Cheapest route$4.1989/1M$1.00225/1M

Privacy posturehas provider E2EE routeprovider posture varies

Fastest measured p50 TTFT1110 ms via telnyx1155 ms via digitalocean

Highest measured throughput182 tok/s via basetennot enough data

Recent route uptime range100.00%50.00%

Modes chat chat

MoonshotAI: Kimi K2.6 routes

Overview32 endpoints
PricingPrompt and completion rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

Nemotron-3-Super-120B routes

Overview2 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

Related comparisons

Browse every comparison

MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5.285 combined provider routes
MoonshotAI: Kimi K2.6 vs MoonshotAI: Kimi K369 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs MoonshotAI: Kimi K2.667 combined provider routes
MoonshotAI: Kimi K2.6 vs OpenAI: gpt-oss-120b65 combined provider routes
DeepSeek: DeepSeek V4 Flash 0423 vs MoonshotAI: Kimi K2.662 combined provider routes
DeepSeek: DeepSeek V4 Pro 0423 vs MoonshotAI: Kimi K2.661 combined provider routes
Google: Gemma 4 31B vs MoonshotAI: Kimi K2.660 combined provider routes
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5.156 combined provider routes

Production choice

Pick a default model. Keep fallback enabled.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

OpenAI clientPython

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)

response = client.chat.completions.create(
    model="moonshotai/kimi-k2.6",
    messages=messages,
)

Questions

Which should I use, MoonshotAI: Kimi K2.6 or Nemotron-3-Super-120B?

Is MoonshotAI: Kimi K2.6 or Nemotron-3-Super-120B cheaper?

The current cheapest TrustedRouter route is $4.1989/1M for MoonshotAI: Kimi K2.6 and $1.00225/1M for Nemotron-3-Super-120B. The comparison uses current catalog prices and updates as provider pricing changes.

Is MoonshotAI: Kimi K2.6 or Nemotron-3-Super-120B faster?

Current measured p50 time to first token is 1110 ms for MoonshotAI: Kimi K2.6 and 1155 ms for Nemotron-3-Super-120B. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test MoonshotAI: Kimi K2.6 and Nemotron-3-Super-120B with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between moonshotai/kimi-k2.6 and nvidia/nemotron-3-super-120b. This makes side-by-side evals possible without maintaining two provider integrations.