kagi · Balanced
Web Answer
Fast web answers with citations, tuned for factual questions and quick summaries.
- Input
- Text
- Output
- Text
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $7.50
- Output
- $7.50
Reference prices as published by the model provider. API example
Specifications
- Context window
- —
- Max output
- 32.8K
Side by side
Web Answer compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Web AnswerkagiThis model | GPT-4 TurboOpenAIRemove | |
|---|---|---|
| Provider | kagi | OpenAI |
| Discovery tier | Balanced | Balanced |
| Added | Dec 23, 2025 | Jan 1, 2024 |
| Limits | ||
| Context window | — | 128K |
| Max output | 32.77KBest | 4.1K |
| Pricing, USD per 1M tokens | ||
| Input | $7.50Best | $10.00 |
| Output | $7.50Best | $30.00 |
| Benchmark indexes | ||
| Intelligence Index | — | 7.0 |
| Coding Index | — | 21.5 |
| Capabilities | ||
| Vision | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Web Answer
- GPT-4 Turbo
Intelligence Index
- Web Answer—
- GPT-4 Turbo7.0
Indexes
Coding Index
Composite of the coding evaluations
- Web Answer: —
- GPT-4 Turbo: 21.5
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Web Answer: —
- GPT-4 Turbo: 3.1%
MMLU-Pro
Multi-subject knowledge and reasoning
- Web Answer: —
- GPT-4 Turbo: 69.4%
Coding
LiveCodeBench
Recent competitive programming problems
- Web Answer: —
- GPT-4 Turbo: 29.1%
Math
AIME
Competition mathematics
- Web Answer: —
- GPT-4 Turbo: 15.0%
MATH-500
Competition math problems
- Web Answer: —
- GPT-4 Turbo: 73.7%
Scores from Artificial Analysis, updated Oct 26, 2026.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fastgpt",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="fastgpt",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)kagi
Related models
Other kagi models, starting with the same family.
- BalancedCompare