google logo
google

Google: Gemma 4 31B (free)

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. This model is free to use. 262,144 token context window, maximum output of 32,768 tokens. Higher uptime with 15 providers. Includes independent benchmarks from Artificial Analysis.

Présentation

Caractéristiques du modèle

Contexte
262 144 tokens
Sortie maximale
32 768 tokens
Architecture
text+image+video->text
Tokenizer
Gemma
Limite des connaissances
Non indiqué
Modéré
Non
OPENROUTER

Tarification complète

Tarifs synchronisés depuis OpenRouter, par million de tokens.

Entrée
Gratuit
/M tokens
Sortie
Gratuit
/M tokens
API

Configuration du modèle

Paramètres par défaut

temperature
1
top_p
0.95
top_k
64

Raisonnement

Modéré
Non
Paramètres par défaut
Non
API

Démarrage rapide

Appelez ce modèle via l’API compatible OpenAI d’OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemma-4-31b-it:free","messages":[{"role":"user","content":"Hello!"}]}'
Capacités et modalités

EntréeSortie

Entrée
imagetextvideo
Sortie
text
Raisonnement

Non

API

Paramètres API pris en charge

include_reasoningmax_tokensreasoningresponse_formatseedtemperaturetool_choicetoolstop_p
Fournisseurs disponibles

16 fournisseurs

Fournisseurs en direct sur OpenRouter

Disponibilité, latence, débit et routage évoluent en continu. Consultez la source pour les données en temps réel.

OpenRouter

DeepInfra

fp4
Contexte
262K
Sortie maximale
16K
Entrée
$0.090
Sortie
$0.340
Lecture du cache
$0.050
Écriture du cache
Non indiqué

CoreWeave

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.100
Sortie
$0.340
Lecture du cache
$0.100
Écriture du cache
Non indiqué

Venice

bf16
Contexte
256K
Sortie maximale
8K
Entrée
$0.120
Sortie
$0.360
Lecture du cache
$0.090
Écriture du cache
Non indiqué

Chutes

fp4
Contexte
131K
Sortie maximale
66K
Entrée
$0.120
Sortie
$0.370
Lecture du cache
$0.012
Écriture du cache
Non indiqué

DeepInfra

fp8
Contexte
262K
Sortie maximale
16K
Entrée
$0.130
Sortie
$0.380
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

SiliconFlow

fp8
Contexte
262K
Sortie maximale
236K
Entrée
$0.130
Sortie
$0.400
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

Crusoe

unknown
Contexte
262K
Sortie maximale
262K
Entrée
$0.140
Sortie
$0.400
Lecture du cache
$0.140
Écriture du cache
Non indiqué

Friendli

unknown
Contexte
262K
Sortie maximale
8K
Entrée
$0.140
Sortie
$0.400
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

Novita

bf16
Contexte
262K
Sortie maximale
131K
Entrée
$0.140
Sortie
$0.400
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

Parasail

fp8
Contexte
262K
Sortie maximale
236K
Entrée
$0.150
Sortie
$0.400
Lecture du cache
$0.060
Écriture du cache
Non indiqué

Phala

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$0.150
Sortie
$0.460
Lecture du cache
$0.075
Écriture du cache
Non indiqué

DeepInfra

fp8
Contexte
131K
Sortie maximale
8K
Entrée
$0.270
Sortie
$0.760
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

SambaNova

unknown
Contexte
131K
Sortie maximale
118K
Entrée
$0.380
Sortie
$1.15
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

Together

unknown
Contexte
262K
Sortie maximale
236K
Entrée
$0.390
Sortie
$0.970
Lecture du cache
Non indiqué
Écriture du cache
Non indiqué

ModelRun

fp4
Contexte
262K
Sortie maximale
236K
Entrée
$0.750
Sortie
$1.00
Lecture du cache
$0.750
Écriture du cache
Non indiqué

Cerebras

fp16
Contexte
131K
Sortie maximale
41K
Entrée
$0.990
Sortie
$1.49
Lecture du cache
$0.990
Écriture du cache
Non indiqué
google

modèles

Tous les modèles
google logogoogle

Google: Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

Contexte
1.0M
Entrée
text · image · video · file · audio
Sortie
text
Entrée: $0.750Sortie: $3.75par million de tokens
Voir la fiche du modèle
google logogoogle

Google: Gemini 3.7 Flash (batch)

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

Contexte
1.0M
Entrée
text · image · video · file · audio
Sortie
text
Entrée: $0.188Sortie: $0.938par million de tokens
Voir la fiche du modèle
google logogoogle

Google: Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

Contexte
1.0M
Entrée
text · image · video · file · audio
Sortie
text
Entrée: $0.750Sortie: $3.75par million de tokens
Voir la fiche du modèle
google logogoogle

Google: Gemini 3.6 Flash (batch)

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

Contexte
1.0M
Entrée
text · image · video · file · audio
Sortie
text
Entrée: $0.375Sortie: $1.88par million de tokens
Voir la fiche du modèle