AI Recommendation
Should you use gpt-oss-120b?
gpt-oss-120b is listed for chat, coding workloads and supports a 131K context window.
Use it when OVHcloud AI Endpoints's free tier is enough for evaluation, demos, or light production traffic.
gpt-oss-120b Free API on OVHcloud AI Endpoints
Free APIOpen GPT reasoning model for self-hosted agents and controllable deployments
Free APIOpenAI compatibleReasoningTool callingJSON modeTextReasoning
API Details
Copy-ready connection details
Base URL
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1 Model ID
gpt-oss-120b API format OpenAI-style
Technical Details
gpt-oss-120b specifications
Context window 131K
Max output 32K
Status Online
Family gpt-oss
Knowledge cutoff 2024-06
Released Aug 5, 2025
Last updated Nov 8, 2026
Free listing since Aug 5, 2025
Input text
Output text
Capabilities reasoning, tool calling, structured output, temperature control
Open weights Yes
Weights Hugging Face
Best for
- Chat
- Coding
Strengths & Weaknesses
Strengths
- Useful for coding workflows
- Long context window
- Reasoning mode listed
- Tool calling support
Watch outs
- Free-tier rate limits apply
- Vision support is not listed
Benchmark Overview
Benchmark signals for gpt-oss-120b
Intelligence General reasoning and instruction following
11.6/100 Coding Programming and code generation
30.4/100 Agentic Tool use and multi-step tasks
3.7/100 Speed Observed generation speed
202 tok/s Context Maximum listed context window
131K Pricing
gpt-oss-120b pricing per 1M tokens
Input $0.15 per 1M tokens
Output $0.6 per 1M tokens
Access Available OVHcloud AI Endpoints
Rate limit 2 RPM (anonymous) provider policy
Availability
gpt-oss-120b availability by provider
We found 2 provider listings for gpt-oss-120b. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | gpt-oss-120b | Free tier | 131K | OpenAI-style | 2 RPM (anonymous) |
| | gpt-oss:120b | Free tier | 128K | OpenAI-style | 1 concurrent request, monthly starter credits |
Compare
gpt-oss-120b alternatives to consider
| Model | Provider | Context | Access |
|---|---|---|---|
| gpt-oss:120b | Ollama Cloud | 128K | Free tier |
| Qwen3.5-397B-A17B | OVHcloud AI Endpoints | 262K | Free tier |
| Meta-Llama-3_3-70B-Instruct | OVHcloud AI Endpoints | 131K | Free tier |
| Qwen3.8-27B | OVHcloud AI Endpoints | 262K | Free tier |
| Qwen3.6-27B | OVHcloud AI Endpoints | 262K | Free tier |
Typical Use Cases
gpt-oss-120b use cases
Chat
gpt-oss-120b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Coding
gpt-oss-120b is tagged for coding in this catalog and works with OpenAI-compatible client libraries.
FAQ
gpt-oss-120b free API FAQ
Is gpt-oss-120b free to use?
gpt-oss-120b is listed with free API access on OVHcloud AI Endpoints, subject to the provider's quota and account policy.
What is the gpt-oss-120b model ID?
The model ID shown in this catalog is gpt-oss-120b.
What are the gpt-oss-120b free tier rate limits on OVHcloud AI Endpoints?
The listed free tier limit is 2 RPM (anonymous). Limits can change per account tier, so confirm against the provider dashboard.
What context window does gpt-oss-120b support?
The listed context window is 131K tokens with up to 32K output tokens.
More about gpt-oss-120b
Cerebras offers GPT-oss-120b, a powerful text-based LLM ideal for chat and coding, generating up to 8,000 tokens from 128,000-token contexts at 30 RPM, 14,400 RPD, and 1M TPD, without requiring a credit card and compatible with OpenAI.
For API keys, setup steps, and provider-level limits, see the OVHcloud AI Endpoints provider page.