OpenAI: gpt-oss-120b (free)
Fiabilité
20%
openai/gpt-oss-120b:free
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 to run on a single H100 GPU with native MXFP4 quantization...
🧠 Intelligence & Données
Knowledge Cutoff:
2024-06-30
Tokenizer:
GPT
Moderation:
⚠️ Oui
📅 Cycle de vie
Ajouté le:
05/08/2025
Spécifications
-
Provider & Modalité openai text->text
-
Fenêtre de contexte 131,072 tokens
-
Max Output Tokens 131,072
-
Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
| Modèle | Provider | Input | Output | Contexte | |
|---|---|---|---|---|---|
|
OpenAI: GPT-5.4 Nano
openai/gpt-5.4-nano
|
openai | $0.2000 | $1.2500 | 400,000 | → |
|
OpenAI: GPT-5.4 Mini
openai/gpt-5.4-mini
|
openai | $0.7500 | $4.5000 | 400,000 | → |
|
OpenAI: GPT-5.4 Pro
openai/gpt-5.4-pro
|
openai | $30.0000 | $180.0000 | 1,050,000 | → |
|
OpenAI: GPT-5.4
openai/gpt-5.4
|
openai | $2.5000 | $15.0000 | 1,050,000 | → |
|
Inception: Mercury 2
inception/mercury-2
|
inception | $0.2500 | $0.7500 | 128,000 | → |