meganova · Efficient
Manta Mini 1.0
Lightweight tier optimized for speed and cost.
- Input
- Text
- Output
- Text
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.02
- Output
- $0.16
Reference prices as published by the model provider. API example
Specifications
- Context window
- 8.2K
- Max output
- —
- Average output (7 days)
- 35 tokens
- Longer than 2% of 468 models
Side by side
Manta Mini 1.0 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Manta Mini 1.0meganovaThis model | Solar Pro 4upstageRemove | |
|---|---|---|
| Provider | meganova | upstage |
| Discovery tier | Efficient | Efficient |
| Added | Sep 20, 2025 | Aug 11, 2026 |
| Limits | ||
| Context window | 8.19K | 524.29KBest |
| Max output | — | 131.07K |
| Average output | 35 tokens | 546 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.02Best | $0.03 |
| Output | $0.16 | $0.12Best |
| Cache read | — | $0.006 |
| Performance | ||
| Throughput | — | 102.7 tok/s |
| Time to first token | — | 2.4 s |
| Request success (24h) | 95.8% | 99.9%Best |
| Benchmark indexes | ||
| Intelligence Index | — | 26.6 |
| Capabilities | ||
| Tools | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Manta Mini 1.0
- Solar Pro 4
Intelligence Index
- Manta Mini 1.0—
- Solar Pro 426.6
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Manta Mini 1.0: —
- Solar Pro 4: 13.6%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Manta Mini 1.0: —
- Solar Pro 4: 2.4%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Manta Mini 1.0: —
- Solar Pro 4: 1,093 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Manta Mini 1.0: —
- Solar Pro 4: 1,106 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Manta Mini 1.0: —
- Solar Pro 4: 7.0%
AA-LCRv1.1
Reasoning across long documents
- Manta Mini 1.0: —
- Solar Pro 4: 70.7%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Manta Mini 1.0: —
- Solar Pro 4: 29.8%
GPQA Diamond
Graduate-level science questions
- Manta Mini 1.0: —
- Solar Pro 4: 89.1%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Manta Mini 1.0: —
- Solar Pro 4: 0.0%
SciCode
Scientific computing in Python
- Manta Mini 1.0: —
- Solar Pro 4: 48.0%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Manta Mini 1.0: —
- Solar Pro 4: 70.7%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Request success (24h)
- 95.8%
- Reliable
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
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": "meganova-ai/manta-mini-1.0",
"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="meganova-ai/manta-mini-1.0",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)meganova
Related models
Other meganova models, starting with the same family.