Model Selection
How to choose the right model for your use case on NexGate
Choosing a Model
NexGate supports models across multiple providers. Use direct model IDs — there are no aliases or tiers to manage.
Note
The full live catalog is always available at GET /api/models or the models page.
Quick Reference
| Model | Best for | Input/1M | Output/1M |
|---|---|---|---|
llama-4-scout | High-volume, low-cost chat | $0.10 | $0.35 |
deepseek-v4-flash | Fast low-cost edits | $0.14 | $0.28 |
gpt-4.1-nano | Classification, routing | $0.10 | $0.40 |
gpt-5.4-mini | Balanced production work | $0.40 | $1.60 |
deepseek-v3.2 | Efficient code generation | $0.28 | $0.42 |
gpt-5.5 | High-quality reasoning | $5.00 | $30.00 |
gpt-4o | Multimodal flagship | $2.50 | $10.00 |
grok-4-3 | Fast frontier chat | $1.25 | $2.50 |
kimi-k2.5 | Long-context multilingual | $0.60 | $2.50 |
How to Use
Pass any supported model ID directly in your request:
from openai import OpenAI
client = OpenAI(
api_key="ng-your-key",
base_url="https://api.nexgate.app/v1"
)
response = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Explain quantum computing"}]
)import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'ng-your-key',
baseURL: 'https://api.nexgate.app/v1'
});
const response = await client.chat.completions.create({
model: 'gpt-5.5',
messages: [{ role: 'user', content: 'Explain quantum computing' }]
});curl https://api.nexgate.app/v1/chat/completions \
-H "Authorization: Bearer ng-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.5",
"messages": [{"role": "user", "content": "Explain quantum computing"}]
}'Recommendations by Use Case
| Use Case | Recommended Model |
|---|---|
| High-volume chatbot | llama-4-scout |
| Simple extraction / classification | gpt-4.1-nano or deepseek-v4-flash |
| General production app | gpt-5.5 |
| Code review / debugging | gpt-5.5 |
| Long-context documents | kimi-k2.5 or kimi-k2.6 |
| Complex reasoning | gpt-5.5 or grok-4-20-reasoning |