openai logo
openai

OpenAI: gpt-oss-20b (batch)

来源介绍(英文)

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

模型概览

模型规格

上下文
131,072 tokens
最大输出
117,964 tokens
架构
text->text
分词器
GPT
知识截止时间
2024-06-30
内容审核
OPENROUTER

完整价格

同步自 OpenRouter。Token 价格均按每百万 Token 展示。

输入
$0.024
每百万 Token
输出
$0.112
每百万 Token
API

模型配置

推理能力

是否必须推理
默认参数
medium
能力与模态
high, medium, low
API

快速调用

在本地设置 OPENROUTER_API_KEY。Python 需安装 requests;JavaScript 在 Node.js 中运行。密钥应保存在服务端。

此请求使用基础模型 ID 提交异步批处理。返回任务 ID 表示已提交,不表示已完成。

API 文档

curl --fail-with-body https://openrouter.ai/api/beta/batches \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"endpoint":"/v1/chat/completions","model":"openai/gpt-oss-20b","requests":[{"custom_id":"request-1","body":{"messages":[{"role":"user","content":"Hello!"}]}}]}'

# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/beta/batches/JOB_ID" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY"
能力与模态

输入输出

输入
text
输出
text
推理能力

· high · medium · low

API

支持的 API 参数

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
可用提供方

1 提供方

核验日期: 2026年9月23日

在 OpenRouter 查看实时 Provider

Provider 可用性、延迟、吞吐量和路由会持续变化,请前往来源页面查看实时运行数据。

OpenRouter

DeepInfra

bf16
上下文
131K
最大输出
118K
输入
$0.024
输出
$0.112
缓存读取
暂未提供
缓存写入
暂未提供
openai

4 个模型

全部模型
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

上下文
1.1M
输入
file · image · text
输出
text
输入: $0.1输出: $0.5每百万 Token
查看模型详情
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

上下文
1.1M
输入
file · image · text
输出
text
输入: $0.05输出: $0.25每百万 Token
查看模型详情
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...

上下文
1.1M
输入
file · image · text
输出
text
输入: $0.1输出: $0.5每百万 Token
查看模型详情
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...

上下文
1.1M
输入
file · image · text
输出
text
输入: $0.05输出: $0.25每百万 Token
查看模型详情