Pricing and availability as of
Lightweight open-source 20B model with reasoning support for efficient inference.
gpt-oss-20bCompare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.
2 providers · select a column to sort
| Provider | Actions | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 128k | — | $0.04 | $0.19 | $0.01 | |||||
| 131.1k | 32.8k | $0.10 | $0.50 | — |
Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.
GPT OSS 20B API pricing starts at $0.04 per 1M input tokens and $0.19 per 1M output tokens through LLM Gateway, on Consensus Protocol. Cached input starts at $0.01 per 1M tokens.
| Provider | Input / 1M tokens | Output / 1M tokens | Cached input / 1M tokens | Context window |
|---|---|---|---|---|
| Consensus Protocol | $0.04 | $0.19 | $0.01 | 128,000 tokens |
| Groq | $0.10 | $0.50 | — | 131,072 tokens |
| Monthly usage | Cost on Consensus Protocol |
|---|---|
| 1M input + 250K output tokens | $0.0875 |
| 10M input + 2.5M output tokens | $0.875 |
| 100M input + 25M output tokens | $8.75 |
Lightweight open-source 20B model with reasoning support for efficient inference. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for GPT OSS 20B on LLM Gateway starts at $0.04 per million input tokens and $0.19 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
GPT OSS 20B supports a context window of up to 131,072 tokens on its largest provider deployment.
GPT OSS 20B is served by Consensus Protocol, Groq through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
GPT OSS 20B supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
GPT OSS 20B was released on August 5, 2025.