OpenAIGPT-OSSchatOpen Weight
GPT-OSS 120B
Canonical Model Slug: gpt-oss-120b · License Source: OpenAI GPT-OSS Official Release (Apache 2.0 Open-Weight Release)
Vision: NoTool Calling: YesReasoning: YesPrompt Caching: Yes
收錄報價總數36across 27 providers
可比較標準報價數36USD / 1M Token basis
最低 Input / 1M$0.03Standard tier min
最低 Output / 1M$0.17Standard tier min
最大 Context Window131,072Max tokens
Max Output Tokens131,072Completion limit
國網 TAIWAN AI RAP 報價
gpt-oss-120b$2.00 / 1M(NT$64 / 1M)輸入與輸出同價· 輸入價排名第 36 / 36
跨供應商 Input / Output 費率視覺化比較 (USD / 1M Tokens)
Showing top 14 comparable offerings sorted by input price；🏛️ 國網以紫色標示並固定顯示
跨供應商價格比較表 (36)
所有價格均可追溯至 LiteLLM 或國網中心原始紀錄，國網報價固定置頂。勾選多列可鎖定圖表比較，點擊「原始紀錄」可檢視完整 JSON 欄位。
| Select | Marketplace · Underlying | Context Window | 計價方案 (Tier) · Region | 操作 | |||
|---|---|---|---|---|---|---|---|
NCHC TAIWAN AI RAP國網 gpt-oss-120b | TAIWAN AI RAP Inference: NCHC | $2.00 | $2.00 | 131,072 | StandardTaiwan | ||
Ollama ollama/gpt-oss:120b-cloud | Local / Self-Hosted Inference: Local Hardware / Ollama Cloud | Free | Free | 131,072 | StandardGlobal | ||
OpenRouter openrouter/openai/gpt-oss-120b:batch | OpenRouter Marketplace Inference: Not Specified | $0.0296 | $0.136 | 131,072 | BatchGlobal | ||
Weights & Biases (Weave) wandb/openai/gpt-oss-120b | W&B Inference Inference: Not Specified | $0.03 ★ 最低價 | $0.17 ★ 最低價 | 131,000 | StandardGlobal | ||
DeepInfra deepinfra/openai/gpt-oss-120b | DeepInfra Serverless Inference: DeepInfra | $0.037 | $0.17 ★ 最低價 | 131,072 | StandardGlobal | ||
OpenRouter openrouter/openai/gpt-oss-120b | OpenRouter Marketplace Inference: Not Specified | $0.037 | $0.17 ★ 最低價 | 131,072 | StandardGlobal | ||
Novita AI novita/openai/gpt-oss-120b | Novita AI Inference: Novita AI | $0.05 | $0.25 | 131,072 | StandardGlobal | ||
Sail sail/openai/gpt-oss-120b | Sail Inference: Sail | $0.06 | $0.40 | 131,072 | StandardGlobal + Cache / Batch rates | ||
OVHcloud AI Endpoints ovhcloud/gpt-oss-120b | OVHcloud Inference: OVHcloud | $0.08 | $0.40 | 131,000 | StandardGlobal | ||
Google Vertex AI (MaaS) vertex_ai/openai/gpt-oss-120b-maas | Google Cloud Vertex AI Inference: Google Cloud | $0.09 | $0.36 | 131,072 | StandardGlobal + Cache / Batch rates | ||
Baseten baseten/openai/gpt-oss-120b | Baseten Model APIs Inference: Baseten | $0.10 | $0.50 | 128,072 | StandardGlobal + Cache / Batch rates | ||
Azure AI Foundry azure_ai/gpt-oss-120b | Microsoft Azure AI Inference: Microsoft Azure | $0.15 | $0.60 | 131,072 | StandardGlobal | ||
Fireworks AI fireworks_ai/accounts/fireworks/models/gpt-oss-120b | Fireworks AI Inference: Fireworks AI | $0.15 | $0.60 | 131,072 | StandardGlobal + Cache / Batch rates | ||
Fireworks AI fireworks_ai/gpt-oss-120b | Fireworks AI Inference: Fireworks AI | $0.15 | $0.60 | 131,072 | StandardGlobal + Cache / Batch rates | ||
Groq groq/openai/gpt-oss-120b | GroqCloud Inference: Groq LPU | $0.15 | $0.60 | 131,072 | StandardGlobal + Cache / Batch rates | ||
Nebius AI Studio nebius/openai/gpt-oss-120b | Nebius AI Studio Inference: Nebius | $0.15 | $0.60 | 131,072 | StandardGlobal | ||
AWS Bedrock (Converse) openai.gpt-oss-120b-1:0 | AWS Bedrock Inference: AWS Bedrock | $0.15 | $0.60 | 128,000 | StandardGlobal | ||
Together AI together_ai/openai/gpt-oss-120b | Together AI Cloud Inference: Together AI | $0.15 | $0.60 | 131,072 | StandardGlobal | ||
Scaleway Generative APIs scaleway/openai/gpt-oss-120b | Scaleway Inference: Scaleway | $0.15 | $0.60 | 128,000 | StandardGlobal | ||
AWS Bedrock (Mantle) bedrock_mantle/openai.gpt-oss-120b | AWS Bedrock Inference: AWS Bedrock | $0.15 | $0.60 | 131,072 | StandardGlobal | ||
TensorMesh tensormesh/openai/gpt-oss-120b | TensorMesh Inference: TensorMesh | $0.15 | $0.60 | 131,072 | StandardGlobal + Cache / Batch rates | ||
DeepInfra deepinfra/openai/gpt-oss-120b-Turbo | DeepInfra Serverless Inference: DeepInfra | $0.15 | $0.60 | 131,072 | TurboGlobal | ||
Databricks databricks/databricks-gpt-oss-120b | Databricks Model Serving Inference: Databricks | $0.15001 | $0.59997 | 131,072 | StandardGlobal + Cache / Batch rates | ||
IBM watsonx.ai watsonx/openai/gpt-oss-120b | IBM Cloud Inference: IBM watsonx | $0.159 | $0.636 | 131,072 | StandardGlobal | ||
Azure AI Foundry azure_ai/FW-GPT-OSS-120B | Microsoft Azure AI Inference: Microsoft Azure | $0.165 | $0.66 | 131,072 | StandardGlobal + Cache / Batch rates | ||
Replicate replicate/openai/gpt-oss-120b | Replicate Inference: Replicate | $0.18 | $0.72 | 131,072 | StandardGlobal | ||
AWS Bedrock (Converse) us-gov.openai.gpt-oss-120b-1:0 | AWS Bedrock Inference: AWS Bedrock | $0.18 | $0.72 | 128,000 | Standardus-gov | ||
AWS Bedrock bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0 | AWS Bedrock Inference: AWS Bedrock | $0.18 | $0.72 | 128,000 | Standardus-gov-west-1 | ||
AWS Bedrock bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0 | AWS Bedrock Inference: AWS Bedrock | $0.18 | $0.72 | 128,000 | Standardus-gov-east-1 | ||
AWS Bedrock (Mantle) bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b | AWS Bedrock Inference: AWS Bedrock | $0.18 | $0.72 | 131,072 | Standardus-gov-west-1 | ||
AWS Bedrock (Mantle) bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b | AWS Bedrock Inference: AWS Bedrock | $0.18 | $0.72 | 131,072 | Standardus-gov-east-1 | ||
DeepInfra deepinfra/openai/gpt-oss-120b-Ultra | DeepInfra Serverless Inference: DeepInfra | $0.20 | $0.95 | 131,072 | UltraGlobal | ||
SambaNova sambanova/gpt-oss-120b | SambaNova Cloud Inference: SambaNova RDU | $0.22 | $0.59 | 131,072 | StandardGlobal | ||
Cerebras cerebras/gpt-oss-120b | Cerebras Cloud Inference: Cerebras Wafer-Scale | $0.35 | $0.75 | 131,072 | StandardGlobal | ||
Cloudflare Workers AI cloudflare/@cf/openai/gpt-oss-120b | Cloudflare Workers AI Inference: Cloudflare | $0.35 | $0.75 | 128,000 | StandardGlobal | ||
Crusoe Cloud crusoe/openai/gpt-oss-120b | Crusoe Cloud Inference: Crusoe | $0.80 | $0.80 | 131,072 | StandardGlobal |
同系列獨立變體與不同參數規模模型（嚴格分離、不強制合併）
依據平台標準化規則，不同參數規模（如 20B 與 120B）、Safeguard 安全微調版、Preview 版與 GGUF 量化版本皆維持獨立比較，不混入上方報價表。
GPT-OSS 20B
gpt-oss-20b
Open Weight25 offerings
GPT OSS 20B MXFP4 GGUF
gpt-oss-20b-mxfp4-gguf
Open Weight1 offerings
GPT OSS 120B MXFP GGUF
gpt-oss-120b-mxfp-gguf
Open Weight1 offerings
GPT-OSS Safeguard 20B
gpt-oss-safeguard-20b
Open Weight5 offerings
GPT-OSS Safeguard 120B
gpt-oss-safeguard-120b
Open Weight4 offerings