Skip to content
OpenSmartRoute

Cost estimator

Know what a request costs before you send it.

Paste a prompt. The router estimates tokens, scores every target and quotes each one with its price split into input and output, expected quality and latency, then names the recommended, cheapest capable, best-quality and fastest picks.

Your request

Nothing is executed and the prompt is not stored. Tokens are estimated from the text; costs use each model's list price.

Anonymous quotes are rate limited; sign in to apply your tenant rules.

Know the price before you send

The router reads your prompt, estimates tokens, scores every model, agent and skill in the catalogue and quotes each one with its expected quality and latency.

Recommended models

What the router picks per use case

Live quotes of representative prompts against this deployment's catalogue, recomputed every minute. Rankings follow the targets, list prices and learned quality, not a hand-maintained list.

Everyday assistant
Meta
On-prem private model

Llama 3.3 70B Instruct

Recommended
per request
$0.00013
quality
0.66
latency
1.20 s

no rule matched · domain=0.50 action=0.50 complexity_fit=1.00 prior=0.70 · best_sim=0.06 top3_mean=0.02

Coding and refactoring
OpenAI
Frontier reasoning model

GPT-4.1

Recommended
per request
$0.00175
quality
0.73
latency
2.50 s

no rule matched · domain=1.00 action=1.00 complexity_fit=0.97 prior=0.93 · best_sim=0.04 top3_mean=0.03

Analysis and reasoning
OpenAI
Frontier reasoning model

GPT-4.1

Recommended
per request
$0.00291
quality
0.78
latency
2.50 s

no rule matched · domain=1.00 action=1.00 complexity_fit=1.00 prior=0.93 · best_sim=0.19 top3_mean=0.10

Summaries and rewriting
Meta
On-prem private model

Llama 3.3 70B Instruct

Recommended
per request
$0.0000553
quality
0.76
latency
1.20 s

no rule matched · domain=1.00 action=1.00 complexity_fit=1.00 prior=0.70 · best_sim=0.16 top3_mean=0.08

Extraction and classification
Meta
On-prem private model

Llama 3.3 70B Instruct

Recommended
per request
$0.0000439
quality
0.86
latency
1.20 s

rule 'pii-stays-onprem' prefers · domain=0.50 action=1.00 complexity_fit=1.00 prior=0.70 · best_sim=0.19 top3_mean=0.09

Sensitive data
Meta
On-prem private model

Llama 3.3 70B Instruct

Recommended
per request
$0.0000678
quality
0.89
latency
1.20 s

rule 'pii-stays-onprem' prefers · domain=1.00 action=1.00 complexity_fit=1.00 prior=0.70 · best_sim=0.12 top3_mean=0.08

Most recommended across use cases

  1. 1Meta
    On-prem private model

    router's pick for 4 use cases · cheapest 4x · best quality 4x

    llm
  2. 2OpenAI
    Frontier reasoning model

    router's pick for 2 use cases · cheapest 2x · best quality 2x

    llm
  3. 3OpenAI
    Mid-tier model

    1 placements

    llm

Quote from code

The same quote is one call away: anonymous quotes are rate limited per client, keyed quotes apply your tenant rules and show up in your usage.

POST /api/v1/estimatebash
curl -s /api/v1/estimate -H "Authorization: Bearer $OSR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Summarise this contract...", "monthly_requests": 50000}'

Or from the SDK and your IDE

osr estimate quotes against a local catalogue and the MCP server exposes estimate and recommend tools to VS Code, Cursor and Claude.

opensmartroute.estimatepython
from opensmartroute.estimate import estimate

q = estimate(router, "Summarise this contract...", output_tokens=300)
print(q.recommended.name, q.recommended.cost_usd, q.savings_usd)

Set up the IDE integration under Integrations or read the MCP guide.