gpt-oss-20bOpenAI
- endpoints
- 2
- regions
- 1
- api
- chat
- released
- August 2025
capabilities 4/8
The same weights cost 1.4x more on groq inc. than on fireworks ai. That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  Fireworks AI | Global | 131K | $0.07 | $0.30 | $0.04 | zdr |
| 2 |  Groq Inc. | Global | 131K | $0.10 | $0.50 | $0.10 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| MMLU Pro | 71.8 | |
| LiveCodeBench | 65.2 | |
| Math Index | 62.3 | |
| AIME 2025 | 62.3 | |
| GPQA Diamond | 61.1 | |
| τ²-Bench | 50.3 | |
| Intelligence Index | 10.0 | |
| Humanity's Last Exam | 5.3 | |
| Terminal-Bench Hard | 4.5 | |
| 9 evals | mean | 43.6 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-08-05.
fireworks/gpt-oss-20bthis model has no managed policy yet, so call the provider endpoint directly. every id in the endpoints table works the same way
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="fireworks/gpt-oss-20b", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
GPT-OSS-20B is OpenAI's lightweight open-weight model with 21.5 billion total parameters (3.6 billion active, Mixture-of-Experts). Optimized for lower latency and local or specialized use cases including agentic tasks, chain-of-thought reasoning, and web browsing. Released under Apache 2.0 license.
questions 5
Which providers serve gpt-oss-20b?
How much does gpt-oss-20b cost?
Is gpt-oss-20b open weights?
What is the context window of gpt-oss-20b?
How do I use gpt-oss-20b with the OpenAI SDK?
more from openai 6
| model | context | from /M | providers |
|---|---|---|---|
| gpt-6-astra | 1.1M | $5.00 | 2 |
| gpt-5.6-luna | 1.1M | $0.10 | 3 |
| gpt-5.6-terra | 1.1M | $1.00 | 3 |
| gpt-5.6-sol | 1.1M | $2.50 | 3 |
| gpt-5.5-pro | 1.1M | $30.00 | 1 |
| gpt-5.5 | 1.1M | $2.50 | 3 |
route gpt-oss-20b through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology