Verified 2026-11-18 · rates follow the live catalog
OpenAI open-weight 20B reasoning model for low-latency agentic and specialized use cases.
| Provider | OpenAI |
|---|---|
| Context window | 128K |
| Input / 1M tokens | $0.20 |
| Output / 1M tokens | $0.30 |
| Cached input / 1M tokens | — |
| Off-peak | 90% off at every hour |
| Reasoning tiers | high,medium,low |
A call with 50,000 input tokens and 10,000 output tokens bills at $0.013: 50,000 ÷ 1,000,000 × $0.20 for input, plus 10,000 ÷ 1,000,000 × $0.30 for output. The 90% off at every hour discount applies to requests outside the peak window, so batch work scheduled into those hours costs measurably less.
Both API formats are served from one host and one key, so a tool that speaks either works without a translation layer:
https://api.openference.com/v1/chat/completionshttps://api.openference.com/v1/messagesSet OPENAI_BASE_URL or ANTHROPIC_BASE_URL to that host and keep the client library you already use.
Send GPT-OSS-20B in the model field. These aliases resolve to the same model: gpt-oss-20b, GPT-OSS 20B.
Capabilities: tool and function calling, reasoning with high,medium,low effort tiers.
The rest of the catalog, with rates side by side, is on all models.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API