Skip to content
OpenSmartRoute
All models
llmazure/llm-small
OpenAI

Small fast model

OpenAI GPT-4.1 Nano · llm-small

Cheap, fast generalist for simple chat, short answers, classification and extraction.

Executable through /v1/chat/completions PII blocked by policy Tool calling
Try in playground JSON
Price per 1M tokens
$0.20
$0.0002 per 1k
Requests · 30d
0
no traffic
Latency
300 ms
declared
Success rate
n/a
quality prior 0.55

Underlying model

Published by the vendor; the platform bills at the target's declared price.

Catalogue entry
OpenAI

GPT-4.1 Nano

tools

OpenAI openai/gpt-4.1-nano

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Input $/1M
$0.10
Output $/1M
$0.40
Context
1.0M
Max output
33K
Released
Apr 14, 2025
Modalities
imagetextfile
Intelligence index-
Coding index11
Agentic index-

Cached input reads $0.03 per 1M

Traffic over 30 days

Requests per day this target answered on this deployment, with the cost line.

No requests yet. Route something from the playground to see usage here.
Tokens
0
Spend
$0
Previous window
0 req

Routed for

Domains the signal layer detected on requests that ended here.

No routed requests yet. Declared domains: General, General Chat, Customer Support.

Capabilities

DomainsGeneral, General Chat, Customer Support
ActionsQa, Classify, Extract, Summarize, Generation, Translate
Complexity band0.00 - 0.45
Languagesen, ta, hi, es, fr
Context windowundeclared
Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryPublic
Regionsanywhere
PIInot allowed
Max input tokensunlimited
Tenantsall

Representative prompts

Examples the similarity strategy matches against.

  • Hi, how are you today?
  • What is the capital of France?
  • Is this email spam? 'Congratulations you won a prize'
  • Summarize this paragraph in one sentence.

Call it

Pin this target with model="llm-small", or send a candidate list and let the router choose and fall back.

curlbash
curl https://api.opensmartroute.ai/v1/chat/completions \
  -H "Authorization: Bearer $OSR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "llm-small", "messages": [{"role": "user", "content": "Hi, how are you today?"}]}'
OpenAI SDKpython
from openai import OpenAI

client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
    model="llm-small",            # pin this target, or "auto" to let the router choose
    messages=[{"role": "user", "content": "Hi, how are you today?"}],
    extra_body={"models": ["llm-small", "auto"]},   # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)