Instamodel
Manage keysTry public demo
Skip to comparison
COMPARE / ROUTE / RECEIPT

Put the right model
to the same test.

Run frontier and specialist models side by side. Every response keeps its provider route, token usage, cost, and latency attached.

Browse full catalog
03 / COMPARE

Response matrix

Execution modeLocal previews

Ready for the public deterministic demo and clearly labeled local previews.

A
Shelfwise Studio

MerchCopy 24B

Post-trained
192K context$0.29 in$0.74 out
ResponseLocal simulation

LOCAL SIMULATION — no request was sent to MerchCopy 24B. This preview demonstrates the response surface only. A live request would route the prompt to shelfwise-demo/merch-copy-24b, then return the provider's generated text with metered token, cost, and latency data.

Usage receiptsim_a_shelfwise_demo_merch_copy_24b
Input
43
tokens
Output
112
tokens
Total
155
tokens
Cost
<$0.0001
USD
Latency
307
ms
Served byBaseten

Local simulation; balanced preference would be recorded but does not switch providers in the private alpha

B
OpenAI

GPT-5.6 Sol

Frontier
1.05M context$5.00 in$30.00 out
ResponseLocal simulation

LOCAL SIMULATION — no request was sent to GPT-5.6 Sol. This preview demonstrates the response surface only. A live request would route the prompt to openai/gpt-5.6, then return the provider's generated text with metered token, cost, and latency data.

Usage receiptsim_b_openai_gpt_5_6
Input
43
tokens
Output
148
tokens
Total
191
tokens
Cost
$0.0047
USD
Latency
1463
ms
Served byOpenAI

Local simulation; balanced preference would be recorded but does not switch providers in the private alpha

OPENAI-COMPATIBLEPOST /api/v1/chat/completions

Change the model ID, not your application. Routing preferences travel with the request and the receipt comes back with the response.