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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
from openai import OpenAI client = OpenAI( base_url="https://api.respan.ai/api/", api_key="YOUR_RESPAN_API_KEY",) response = client.chat.completions.create( model="tera/openai/gpt-oss-120b", messages=[{"role": "user", "content": "Hello!"}],)print(response.choices[0].message.content)from openai import OpenAI client = OpenAI( base_url="https://api.respan.ai/api/", api_key="YOUR_RESPAN_API_KEY",) response = client.chat.completions.create( model="tera/openai/gpt-oss-120b", messages=[{"role": "user", "content": "Hello!"}],)print(response.choices[0].message.content)Gateway routes for this model on the Respan gateway, including fallback routes when configured.
| Model | Capabilities | ||||||
|---|---|---|---|---|---|---|---|
| tera/openai/gpt-oss-120b | 131K | $0.09/M | $0.36/M | Read:$0.00/MWrite:$0.00/M | — | — |
Other models from the same provider available through the gateway.
| Model | Capabilities | ||||||
|---|---|---|---|---|---|---|---|
| tera/anthropic/claude-fable-5 | 200K | $10.00/M | $50.00/M | Read:$1.00/MWrite:$0.00/M | — | — | |
| tera/anthropic/claude-opus-4-8 | 200K | $5.00/M | $25.00/M | Read:$0.50/MWrite:$0.00/M | — | — | |
| tera/anthropic/claude-sonnet-5 | 200K | $2.00/M | $10.00/M | Read:$0.20/MWrite:$0.00/M | — | — | |
| tera/deepseek-ai/DeepSeek-R1-0528 | 164K | $1.35/M | $5.40/M | Read:$0.00/MWrite:$0.00/M | — | — | |
| tera/deepseek-ai/DeepSeek-V3.1 | 164K | $0.60/M | $1.70/M | Read:$0.06/MWrite:$0.00/M | — | — | |
| tera/deepseek-ai/DeepSeek-V3.2 | 164K | $0.56/M | $1.68/M | Read:$0.06/MWrite:$0.00/M | — | — | |
| tera/deepseek-ai/DeepSeek-V4-Flash | 1.0M | $0.19/M | $0.51/M | Read:$0.03/MWrite:$0.00/M | — | — | |
| tera/deepseek-ai/DeepSeek-V4-Pro | 1.0M | $1.74/M | $3.48/M | Read:$0.14/MWrite:$0.00/M | — | — | |
| tera/google/gemma-4-26B-A4B-it | 262K | $0.15/M | $0.60/M | Read:$0.01/MWrite:$0.00/M | — | — | |
| tera/meta-llama/Llama-3.3-70B-Instruct | 128K | $0.72/M | $0.72/M | Read:$0.00/MWrite:$0.00/M | — | — | |
| tera/MiniMaxAI/MiniMax-M2 | 197K | $0.30/M | $1.20/M | Read:$0.03/MWrite:$0.00/M | — | — | |
| tera/moonshotai/kimi-k2-thinking | 262K | $0.60/M | $2.50/M | Read:$0.06/MWrite:$0.00/M | — | — |
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.