Open GPT reasoning model for self-hosted agents and controllable deployments
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1 gpt-oss-20b gpt-oss-20b is listed for chat, coding workloads and supports a 128K context window.
Check OVHcloud AI Endpoints's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We found 3 provider listings for gpt-oss-20b. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | gpt-oss-20b | Check provider | 128K | OpenAI-style | 2 RPM (anonymous) |
| | gpt-oss:20b | Free tier | 131K | OpenAI-style | Session/weekly limits (unpublished) |
| | GPT OSS 20B | Free tier | 131K | Native | Varies |
| Model | Provider | Context | Access |
|---|---|---|---|
| gpt-oss:20b | Ollama Cloud | 131K | Free tier |
| GPT OSS 20B | LLM7.io | 131K | Free tier |
| Qwen3.5-397B-A17B | OVHcloud AI Endpoints | 131K | Free tier |
| Meta-Llama-3_3-70B-Instruct | OVHcloud AI Endpoints | 131K | Free tier |
| Qwen3.6-27B | OVHcloud AI Endpoints | 131K | Free tier |
gpt-oss-20b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
gpt-oss-20b is tagged for coding in this catalog and works with OpenAI-compatible client libraries.
gpt-oss-20b appears in the free model catalog for OVHcloud AI Endpoints, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is gpt-oss-20b.
The listed free tier limit is 2 RPM (anonymous). Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 8K output tokens.
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
For API keys, setup steps, and provider-level limits, see the OVHcloud AI Endpoints provider page.