GPT OSS 20B
$0.225
estimated usage cost
1,000 requests × (1,000 uncached input × $0.075 + 500 output × $0.30) / 1,000,000 = $0.225
base rates; no context pricing tiers are published.
Text generation / OpenAI
GPT OSS 20B is a text generation model from OpenAI, available through the Impossibl API. Its published context window is 128,000 tokens. The advertised input rate is $0.075 per million input tokens. The advertised output rate is $0.30 per million output tokens.
api id: openai/gpt-oss-20b
published base api rates · usd per 1m tokens
rates are published by the impossibl api. balance-purchase fees, taxes, tool charges, and workspace-specific pricing are separate.
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports.
estimate text token usage for your workload. all amounts are in usd.
$0.225
estimated usage cost
1,000 requests × (1,000 uncached input × $0.075 + 500 output × $0.30) / 1,000,000 = $0.225
base rates; no context pricing tiers are published.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
Results from Artificial Analysis. Each configuration is listed separately. These evaluations describe the tested model configuration; performance and costs can differ on Impossibl. Last checked 2026-09-11.
| Benchmark | Score |
|---|---|
| Intelligence Index | 9.04 |
| Omniscience Index | -63.05 |
| GPQA | 68.79% |
| Humanity’s Last Exam | 10.98% |
| SciCode | 38.89% |
| CritPt | 1.43% |
| Terminal-Bench v2.1 | 13.86% |
| Terminal-Bench v4.0 | 0.00% |
| Terminal-Bench Hard | 10.61% |
| AA-LCR | 34.67% |
| Multilingual LCR | 0.56% |
| GDPval Elo | 513.93 |
| GDP.pdf All-pass | 2.00% |
| AutomationBench Partial | 0.19% |
| IFBench | 65.10% |
| Tau2 | 60.23% |
| Tau Banking | 7.01% |
| APEX-Agents | 0.74% |
| LiveCodeBench | 77.67% |
| AIME 2025 | 89.33% |
| coding index (API) | 20.7 |
| agentic index (API) | 1.4 |
| intelligence index (API) | 9 |
Unmeasured scores are omitted. API values retain their source units.
view source ↗| Benchmark | Score |
|---|---|
| Intelligence Index | 9.95 |
| Omniscience Index | -58.55 |
| GPQA | 61.11% |
| Humanity’s Last Exam | 5.28% |
| CritPt | 0.00% |
| Terminal-Bench Hard | 4.55% |
| AA-LCR | 31.00% |
| IFBench | 57.82% |
| Tau2 | 50.29% |
| LiveCodeBench | 65.19% |
| AIME 2025 | 62.33% |
| intelligence index (API) | 10 |
Unmeasured scores are omitted. API values retain their source units.
view source ↗GPT OSS 20B is a text-generation model from OpenAI, available through the Impossibl API.
GPT OSS 20B costs $0.075 per million input tokens and $0.30 per million output tokens through the Impossibl API. Cache reads cost $0.0375 per million tokens. All rates are in USD.
GPT OSS 20B has a 128,000-token context window through the Impossibl API.
GPT OSS 20B accepts text as input. GPT OSS 20B returns text.
GPT OSS 20B is available through the Impossibl API. Use openai/gpt-oss-20b as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
OpenAI released GPT OSS 20B on August 5, 2025.
this page describes GPT OSS 20B as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.
model descriptions and release dates, where available, use the creator sources linked in the faq. api prices and limits use the impossibl catalog. benchmark results, where available, are credited to Artificial Analysis in the benchmarks section. report a correction →