ComputeLlamaJSON API

Endpoint / openrouter-latest-google-gemini-pro-latest

Gemini Pro Latest

served by OpenRouter

Default workload estimate$14.001M input + 1M output tokens
Provider model ID
~google/gemini-pro-latest
Protocol
openai chat completions
Region
global
Status
active
Base URL
https://openrouter.ai/api/v1

Current offers

Price components

Exact source values; no hidden currency conversion.

On demandon demand
$14.00
input tokens$2.00per million tokens
output tokens$12.00per million tokens
cached input tokens$0.20per million tokens
cache write tokens$0.38per million tokens

Provider assertions

Claims

compatibility · structured outputs

supported · 1 source assertion

compatibility · tools

supported · 1 source assertion

limits · context tokens

reported · 1 source assertion

modalities · input

reported · 1 source assertion

routing · moderated

unsupported · 1 source assertion

Independent checks

Observations

0

independent observations · probes begin in Stage 2

Immutable record

Pricing history

Newest observed values first.

ObservedOfferComponentPriceSnapshot
On demandinput tokens$2.00476e335527…
On demandoutput tokens$12.00476e335527…
On demandcached input tokens$0.20476e335527…
On demandcache write tokens$0.38476e335527…
On demandinput tokens$2.00476e335527…
On demandoutput tokens$12.00476e335527…
On demandcached input tokens$0.20476e335527…
On demandcache write tokens$0.38476e335527…
On demandinput tokens$2.0093189837d1…
On demandoutput tokens$12.0093189837d1…
On demandcached input tokens$0.2093189837d1…
On demandcache write tokens$0.3893189837d1…
On demandinput tokens$2.0093189837d1…
On demandoutput tokens$12.0093189837d1…
On demandcached input tokens$0.2093189837d1…
On demandcache write tokens$0.3893189837d1…