openai logo
openai

OpenAI: gpt-oss-120b

Descrizione della fonte (inglese)

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Panoramica

Specifiche del modello

Contesto
131.072 tokens
Output massimo
65.536 tokens
Architettura
text->text
Tokenizer
GPT
Limite di conoscenza
2024-06-30
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.15
per milione di token
Output
$0.6
per milione di token
Lettura cache
$0.075
per milione di token
API

Configurazione del modello

Ragionamento

Ragionamento obbligatorio
Parametri predefiniti
medium
Capacità e modalità
high, medium, low
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":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

InputOutput

Input
text
Output
text
Ragionamento

No · high · medium · low

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Provider disponibili

24 provider

Verificato: 18 settembre 2026

Provider live su OpenRouter

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

OpenRouter

AkashML

bf16
Contesto
131K
Output massimo
118K
Input
$0.03
Output
$0.17
Lettura cache
$0.03
Scrittura cache
Non indicato

CoreWeave

fp4
Contesto
131K
Output massimo
118K
Input
$0.03
Output
$0.17
Lettura cache
$0.03
Scrittura cache
Non indicato

DekaLLM

bf16
Contesto
131K
Output massimo
118K
Input
$0.03
Output
$0.18
Lettura cache
Non indicato
Scrittura cache
Non indicato

DeepInfra

bf16
Contesto
131K
Output massimo
118K
Input
$0.037
Output
$0.17
Lettura cache
Non indicato
Scrittura cache
Non indicato

Crusoe

bf16
Contesto
131K
Output massimo
118K
Input
$0.05
Output
$0.25
Lettura cache
$0.05
Scrittura cache
Non indicato

Novita

fp4
Contesto
131K
Output massimo
33K
Input
$0.05
Output
$0.25
Lettura cache
Non indicato
Scrittura cache
Non indicato

Mancer 2

fp8
Contesto
131K
Output massimo
118K
Input
$0.05
Output
$0.3
Lettura cache
Non indicato
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
128K
Output massimo
4K
Input
$0.06
Output
$0.42
Lettura cache
$0.012
Scrittura cache
Non indicato

Google

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.09
Output
$0.36
Lettura cache
Non indicato
Scrittura cache
Non indicato

BaseTen

fp4
Contesto
128K
Output massimo
115K
Input
$0.1
Output
$0.5
Lettura cache
$0.1
Scrittura cache
Non indicato

BaseTen

fp4
Contesto
128K
Output massimo
115K
Input
$0.1
Output
$0.5
Lettura cache
$0.1
Scrittura cache
Non indicato

Parasail

fp4
Contesto
131K
Output massimo
118K
Input
$0.1
Output
$0.75
Lettura cache
$0.055
Scrittura cache
Non indicato

SambaNova

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.14
Output
$0.95
Lettura cache
Non indicato
Scrittura cache
Non indicato

Amazon Bedrock

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.15
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

Nebius

fp4
Contesto
131K
Output massimo
118K
Input
$0.15
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

Amazon Bedrock

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.15
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

DeepInfra

bf16
Contesto
131K
Output massimo
16K
Input
$0.15
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
131K
Output massimo
8K
Input
$0.15
Output
$0.6
Lettura cache
$0.075
Scrittura cache
Non indicato

Phala

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.15
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

Together

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.15
Output
$0.6
Lettura cache
Non indicato
Scrittura cache
Non indicato

Groq

Non indicato
Contesto
131K
Output massimo
66K
Input
$0.15
Output
$0.6
Lettura cache
$0.075
Scrittura cache
Non indicato

Mara

Non indicato
Contesto
131K
Output massimo
118K
Input
$0.15
Output
$0.75
Lettura cache
Non indicato
Scrittura cache
Non indicato

DeepInfra

fp8
Contesto
131K
Output massimo
118K
Input
$0.2
Output
$0.95
Lettura cache
Non indicato
Scrittura cache
Non indicato

Cerebras

fp16
Contesto
131K
Output massimo
41K
Input
$0.35
Output
$0.75
Lettura cache
$0.35
Scrittura cache
Non indicato
openai

4 modelli

Tutti i modelli
openai logoopenai

OpenAI: GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Contesto
1.1M
Input
file · image · text
Output
text
Input: $0.1Output: $0.5per milione di token
Vedi i dettagli del modello
openai logoopenai

OpenAI: GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Contesto
1.1M
Input
file · image · text
Output
text
Input: $0.05Output: $0.25per milione di token
Vedi i dettagli del modello
openai logoopenai

OpenAI: GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

Contesto
1.1M
Input
file · image · text
Output
text
Input: $0.1Output: $0.5per milione di token
Vedi i dettagli del modello
openai logoopenai

OpenAI: GPT-6 Luna (batch)

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

Contesto
1.1M
Input
file · image · text
Output
text
Input: $0.05Output: $0.25per milione di token
Vedi i dettagli del modello