Best Performance

Maximum benchmark performance.

A

Claude Fable 5 High

Anthropic
Arena score vs leader100%1496 Arena scoreThe leader is the 100% reference
API price
$10.00Input / 1M tokens
$50.00Output / 1M tokens
Choose this when the highest Arena score comes first.

Leads the supplied Arena document comparison. Prioritize it when document benchmark performance matters most.

Best Value

A smarter performance-to-cost balance.

K

Kimi K2.6

Moonshot AI
Arena score vs leader97%1451 Arena scoreShare of the leader’s Arena score
Token cost savings
−90.5%Saves on input cost
$0.95Input / 1M tokens
−92%Saves on output cost
$4.00Output / 1M tokens
97% of the leader’s Arena score · 90.5% lower input cost · 92% lower output cost

Kimi is the current supplied value recommendation for documents, with lower input and output token reference prices.

Arena · supplied snapshot·Supplied Arena snapshot · date pending·How we compare

Input and output savings use the separate supplied token rates. Combined cost uses 1M combined tokens: 75% input / 25% output; your workload mix changes the combined savings. Arena scores and prices are from the supplied snapshot. The leaderboard source and snapshot date still need confirmation.

Compare the essentials.

The same workload, with the details that help you choose.

Side-by-side comparison of recommended documents models
ComparisonClaude Fable 5 HighBest PerformanceKimi K2.6Best Value
Arena score1496

Supplied Arena snapshot · date pending

1451

Supplied Arena snapshot · date pending

Relative scorePerformance reference3.0% lower Arena score
Input / 1M tokens$10.00$0.95
Output / 1M tokens$50.00$4.00
Arena differencePerformance reference-45 / -3.0%
Cost differencePrice reference90.5% lower input cost · 92% lower output cost
Supported modalitiestext, image, document → texttext, document → text
Main reason to chooseChoose this when maximum benchmark performance matters more than inference cost.Consider this for production workloads where the reference price matters. Evaluate the benchmark gap against your own workload.
Best fitMaximum benchmark performance for reasoning, coding, visual understanding and documentsDocument extraction, summaries and document reasoning at volume
Billing detailsSupplied reference prices per 1M input and output tokens. No additional percentage discount is applied.Supplied reference prices per 1M input and output tokens. No additional percentage discount is applied.

Input and output savings use the separate supplied token rates. Combined cost uses 1M combined tokens: 75% input / 25% output; your workload mix changes the combined savings.

Implementation

Test your chosen model.

Copy a model test, replace the API key with your own, and run.

Copy the Python or cURL test for Kimi K2.6. Replace the API-key placeholder with your own key and run.

Document text test · The sample document is included in the request as text.

Kimi K2.6 · Python
import json
from urllib.error import HTTPError
from urllib.request import Request, urlopen

API_KEY = "YOUR_ROTEN_API_KEY"

def send(url, payload=None):
    data = json.dumps(payload).encode("utf-8") if payload is not None else None
    request = Request(url, data=data, headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"})
    try:
        with urlopen(request, timeout=180) as response:
            return json.load(response)
    except HTTPError as error:
        raise SystemExit(f"HTTP {error.code}: {error.read().decode('utf-8')}")

payload = json.loads(r'''{
  "messages": [
    {
      "role": "user",
      "content": "Summarize this sample project memo in two bullets.\n\nThe product team is evaluating an AI API for customer-support replies. The trial will compare response usefulness and request cost. Engineering will record the results before selecting a model."
    }
  ],
  "max_tokens": 256,
  "stream": false,
  "model": "kimi-k2.6"
}''')
result = send("https://api.roten.ai/v1/chat/completions", payload)
print(json.dumps(result, indent=2, ensure_ascii=False))

Python tests use the standard library. Video cURL tests also use Python 3 to read task responses.

A clear reference point

Understand the recommendation.

Recommendations combine the supplied Arena scores with the supplied model prices. A benchmark score is one signal for choosing a model for your workload.

Arena · supplied snapshot·Supplied Arena snapshot · date pending·How we compare

Learn how we rank models

Built for production

Running AI at scale?

Talk to us about volume pricing, model selection and migration.

Talk to Sales