Which LLM is the cheapest for our workload?

The best-for pages rank the live catalogue per task by the index that measures it, and the router picks the cheapest model that meets your quality rule for each request.

How much can we save on our LLM bill?

On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.

How often do model prices change?

The catalogue is refreshed from the vendors' price lists; each model page shows the date of its data.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

gpt-oss-20b (self-hosted) (gpt-oss) - OpenSmartRoute

All models

llm

gpt-oss-20b (self-hosted)

gpt-oss · runs as gpt-oss-20b OpenAI

OpenAI's open-weight 20B reasoning model under Apache-2.0, served on our own hardware - strong general reasoning, coding and agentic tool use without data leaving the deployment.

Chosen and quoted; no provider connected yet On Prem boundary May receive personal data Tool calling

Try in playground JSON

Price per 1M tokens: $0.40; the target's declared price; the vendor's list price is below
Requests · 30d: 0; no traffic
Declared latency: 1.80 s; from the catalogue entry; nothing measured here in the window
Success rate: n/a; of the requests it answered; the quality prior is 78% (the router's starting estimate, not a benchmark)

Underlying model

Catalogue entry

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

gpt-oss-20b

reasoning open weights tools

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, Marketing, Finance.

Capabilities

DomainsGeneral, Marketing, Finance

ActionsReasoning, Generation, Summarize, Q&A

Complexity band0.35 - 0.70

Languages*

Context window128K tokens

Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryOn Prem

RegionsUS

PIIallowed

Max input tokensunlimited

Tenantsall

Route to it

This llm is not executed by the platform. Ask the router for a decision restricted to kinds=["llm"] and dispatch the winner in your own stack; send feedback afterwards so the learners improve.

curlbash

curl https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route \
  -H "Authorization: Bearer $OSR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Explain the trade-offs between speculative decoding and batching for a 20B model on one GPU.", "kinds": ["llm"], "top_k": 3}'

# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of llm targets happens in your stack.

httpxpython

import httpx

r = httpx.post(
    "https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route",
    headers={"Authorization": "Bearer osr_live_..."},
    json={"text": "Explain the trade-offs between speculative decoding and batching for a 20B model on one GPU.", "kinds": ["llm"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]])  # e.g. gpt-oss first when it fits

One target among many