openai logo
openai

OpenAI: gpt-oss-120b

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. $0.03 per million input tokens, $0.17 per million output tokens. 131,072 token context window, maximum output of 131,072 tokens. Higher uptime with 18 providers. Includes independent benchmarks from Artificial Analysis.

Panoramica

Specifiche del modello

Contesto
131.072 tokens
Output massimo
117.964 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
$0.03
/M tokens
Output
$0.17
/M tokens
Lettura cache
$0.03
/M tokens
API

Configurazione del modello

Ragionamento

Moderato
Parametri predefiniti
medium
Capacità e modalità
high, medium, low
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di OpenRouter.

curl 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

20 provider

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
$0.030
Output
$0.170
Lettura cache
$0.030
Scrittura cache
Non indicato

CoreWeave

fp4
Contesto
131K
Output massimo
118K
Input
$0.030
Output
$0.170
Lettura cache
$0.030
Scrittura cache
Non indicato

DeepInfra

bf16
Contesto
131K
Output massimo
118K
Input
$0.037
Output
$0.170
Lettura cache
Non indicato
Scrittura cache
Non indicato

Novita

fp4
Contesto
131K
Output massimo
33K
Input
$0.050
Output
$0.250
Lettura cache
Non indicato
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
131K
Output massimo
8K
Input
$0.050
Output
$0.450
Lettura cache
Non indicato
Scrittura cache
Non indicato

DigitalOcean

unknown
Contesto
128K
Output massimo
115K
Input
$0.055
Output
$0.385
Lettura cache
$0.020
Scrittura cache
Non indicato

Mancer 2

fp8
Contesto
131K
Output massimo
118K
Input
$0.065
Output
$0.500
Lettura cache
Non indicato
Scrittura cache
Non indicato

Google

unknown
Contesto
131K
Output massimo
118K
Input
$0.090
Output
$0.360
Lettura cache
Non indicato
Scrittura cache
Non indicato

BaseTen

fp4
Contesto
128K
Output massimo
115K
Input
$0.100
Output
$0.500
Lettura cache
$0.100
Scrittura cache
Non indicato

Parasail

fp4
Contesto
131K
Output massimo
118K
Input
$0.100
Output
$0.750
Lettura cache
$0.055
Scrittura cache
Non indicato

SambaNova

unknown
Contesto
131K
Output massimo
118K
Input
$0.140
Output
$0.950
Lettura cache
Non indicato
Scrittura cache
Non indicato

Amazon Bedrock

unknown
Contesto
131K
Output massimo
118K
Input
$0.150
Output
$0.600
Lettura cache
Non indicato
Scrittura cache
Non indicato

DeepInfra

bf16
Contesto
131K
Output massimo
16K
Input
$0.150
Output
$0.600
Lettura cache
Non indicato
Scrittura cache
Non indicato

Groq

unknown
Contesto
131K
Output massimo
66K
Input
$0.150
Output
$0.600
Lettura cache
$0.075
Scrittura cache
Non indicato

Phala

unknown
Contesto
131K
Output massimo
118K
Input
$0.150
Output
$0.600
Lettura cache
Non indicato
Scrittura cache
Non indicato

Amazon Bedrock

unknown
Contesto
131K
Output massimo
118K
Input
$0.150
Output
$0.600
Lettura cache
Non indicato
Scrittura cache
Non indicato

Together

unknown
Contesto
131K
Output massimo
118K
Input
$0.150
Output
$0.600
Lettura cache
Non indicato
Scrittura cache
Non indicato

Nebius

fp4
Contesto
131K
Output massimo
118K
Input
$0.150
Output
$0.600
Lettura cache
Non indicato
Scrittura cache
Non indicato

Mara

unknown
Contesto
131K
Output massimo
118K
Input
$0.150
Output
$0.750
Lettura cache
Non indicato
Scrittura cache
Non indicato

Cerebras

fp16
Contesto
131K
Output massimo
41K
Input
$0.350
Output
$0.750
Lettura cache
$0.350
Scrittura cache
Non indicato
openai

modelli

Tutti i modelli
openai logoopenai

OpenAI: GPT Transcribe

GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language...

Contesto
Non indicato
Input
audio
Output
transcription
Input: $4500.00Output: Gratuitoper milione di token
Vedi i dettagli del modello
openai logoopenai

OpenAI: GPT-5.6 Luna Pro

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 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: $0.200Output: $1.20per milione di token
Vedi i dettagli del modello
openai logoopenai

OpenAI: GPT-5.6 Luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Contesto
1.1M
Input
file · image · text
Output
text
Input: $0.200Output: $1.20per milione di token
Vedi i dettagli del modello
openai logoopenai

OpenAI: GPT-5.6 Terra Pro

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, 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: $2.00Output: $12.00per milione di token
Vedi i dettagli del modello