Kimi K2.6 vs @cf/nvidia/nemotron-3-120b-a12b

Try both on us. Starter credit covers your first requests, then one key routes Kimi K2.6 and @cf/nvidia/nemotron-3-120b-a12b. Switch by changing the model name.

No card required. Start with 1 million free tokens.

Side by side:

MoonshotAI: Kimi K2.6 compared with @cf/nvidia/nemotron-3-120b-a12b
Attribute	Kimi K2.6 `moonshotai/kimi-k2.6`	@cf/nvidia/nemotron-3-120b-a12b `nvidia/nemotron-3-120b-a12b`
Price, 1M in + out	$2.31 Chutes, cheapest route	$2.11 Cloudflare Workers AI, cheapest route
Input / output, 1M	$0.41 / $1.90	$0.53 / $1.58
Cached input	$0.041145/1M to $0.427223/1M	Not published
Context window	262K 262,144 tokens	256K 256,000 tokens
First token, p50	1.4 s via Kimi	Measuring
AI IQ	IQ 114 #62 on AI IQ	Unrated
Provider routes	16 with failover	1
Privacy	Confidential E2EE and zero retention route	Varies by provider
Recent route uptime range	100.00%	not enough data
Publisher	Kimi	NVIDIA
Modes	chat	chat
More detail	Overview Pricing Providers Benchmarks	Overview

Price adds one million input and one million output tokens on the cheapest route. Prices and speed change: see the monthly reports and run a small eval before you choose a default.

Test both with your agent

Paste this into Claude Code, Cursor or any coding agent.

Compare Kimi K2.6 and @cf/nvidia/nemotron-3-120b-a12b in this project through TrustedRouter.

1. Read https://trustedrouter.com/docs/llms.txt
2. Point the OpenAI-compatible client at
   https://api.trustedrouter.com/v1 and read the key from
   TRUSTEDROUTER_API_KEY.
3. Run our eval prompts on moonshotai/kimi-k2.6, then on nvidia/nemotron-3-120b-a12b.
4. Show me cost, latency and quality side by side before changing the default.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
for model in ("moonshotai/kimi-k2.6", "nvidia/nemotron-3-120b-a12b"):
    response = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "What is the capital of France?"}],
    )
    print(model, response.choices[0].message.content)

for model in moonshotai/kimi-k2.6 nvidia/nemotron-3-120b-a12b; do
  curl https://api.trustedrouter.com/v1/chat/completions \
    -H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{\"model\": \"$model\", \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]}"
done

Your agent will need an API key.

Questions

Which should I use, MoonshotAI: Kimi K2.6 or @cf/nvidia/nemotron-3-120b-a12b?

MoonshotAI: Kimi K2.6 has more Credits provider routes and the larger context window. @cf/nvidia/nemotron-3-120b-a12b has the lower published input-plus-output rate. There is not enough recent probe data to compare speed.

Is MoonshotAI: Kimi K2.6 or @cf/nvidia/nemotron-3-120b-a12b cheaper?

The current cheapest TrustedRouter route is $2.31045/1M for MoonshotAI: Kimi K2.6 and $2.11/1M for @cf/nvidia/nemotron-3-120b-a12b. The comparison uses current catalog prices and updates as provider pricing changes.

Is MoonshotAI: Kimi K2.6 or @cf/nvidia/nemotron-3-120b-a12b faster?

Current measured p50 time to first token is 1416 ms for MoonshotAI: Kimi K2.6 and not enough data for @cf/nvidia/nemotron-3-120b-a12b. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test MoonshotAI: Kimi K2.6 and @cf/nvidia/nemotron-3-120b-a12b 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-3-120b-a12b. This makes side-by-side evals possible without maintaining two provider integrations.

More comparisons

All comparisons

Try Kimi K2.6 and @cf/nvidia/nemotron-3-120b-a12b with one key.

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.

No card required. Start with 1 million free tokens.