AI TOOLS RADAR
Tutti i modelli / GOOGLE
google logo
google

Google: Gemma 3 4B

Descrizione della fonte (inglese)

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Vedi la fonte su OpenRouter Hugging Face
Panoramica

Specifiche del modello

Contesto
131.072 tokens
Output massimo
117.964 tokens
Architettura
text+image->text
Tokenizer
Gemini
Limite di conoscenza
2024-08-31
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.04
per milione di token
Output
$0.05
per milione di token
Lettura cache
$0.02
per milione di token
API

Avvio rapido

Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.

Documentazione API

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemma-3-4b-it","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
textimage
Output
text
API

Parametri API supportati

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p
Provider disponibili

2 provider

Verificato: 20 ottobre 2026

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

Parasail

bf16
Contesto
131K
Output massimo
118K
Input
$0.04
Output
$0.05
Lettura cache
$0.02
Scrittura cache
Non indicato

DeepInfra

bf16
Contesto
131K
Output massimo
16K
Input
$0.05
Output
$0.1
Lettura cache
Non indicato
Scrittura cache
Non indicato
google

4 modelli

Tutti i modelli
google logogoogle

Google: Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Contesto
1.0M
Input
audio · file · image · text · video
Output
text
Input: $2Output: $10per milione di token
Vedi i dettagli del modello →
google logogoogle

Google: Gemini 4 Argon (batch)

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Contesto
1.0M
Input
audio · file · image · text · video
Output
text
Input: $1Output: $5per milione di token
Vedi i dettagli del modello →
google logogoogle

Google: Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

Contesto
66K
Input
image · text
Output
image · text
Input: $1.5 per milione di tokenOutput: $7.5 per milione di token
Vedi i dettagli del modello →
google logogoogle

Google: Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...

Contesto
98K
Input
audio
Output
transcription
Input: $2 per milione di tokenOutput: $12 per milione di token
Vedi i dettagli del modello →