OpenAI: gpt-oss-20b
Analysis Summary
OpenAI's gpt-oss-20b is a text-only model with a 131K context window and support for tool use and function calling. Its measured intelligence index is 15.2, with a coding index of 20.7 and a low agentic index, so it is better suited to bounded tasks than complex reasoning or autonomous workflows.
The low input and output prices make it a candidate for high-volume text processing, basic drafting, and simple tool-connected tasks where cost matters more than answer depth. The provided data does not list vision support, and its coding and agentic measurements do not support using it as a primary software engineering or agent model.
Consider it for inexpensive, clearly scoped workloads with human review. For complex client work, route requests to a model with stronger reasoning and agentic performance.
Assessed September 23, 2026
Editorial notes
gpt-oss-20b offers a 131K context window, tool and function calling, and low API pricing; its measured reasoning, coding, and agentic capabilities are limited.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
gpt-oss-20b offers a 131K context window, tool and function calling, and low API pricing; its measured reasoning, coding, and agentic capabilities are limited.
Benchmarks
Artificial Analysis data refreshed Oct 9, 2026. Arena ratings from the Oct 2, 2026 text leaderboard, with style control.
How OpenAI: gpt-oss-20b compares
OpenAI: gpt-oss-20b ranks #219 of 435 AI models we track for overall intelligence, #132 of 198 for coding, #149 of 181 for agentic tasks. Its 131K-token context window is larger than 51% of the models we list. At $0.02 per million input tokens it is cheaper than 76% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.02 | $0.000018 |
| Output | $0.09 | $0.000090 |
What would OpenAI: gpt-oss-20b cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 697 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save OpenAI: gpt-oss-20b for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout OpenAI: gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for..
Frequently asked questions about OpenAI: gpt-oss-20b
How much does OpenAI: gpt-oss-20b cost?
OpenAI: gpt-oss-20b costs $0.02 per million input tokens and $0.09 per million output tokens.
What is the context window of OpenAI: gpt-oss-20b?
OpenAI: gpt-oss-20b has a context window of 131,072 tokens (131K).
Is OpenAI: gpt-oss-20b good for coding?
On our coding benchmark index, OpenAI: gpt-oss-20b ranks #132 of 198 models, placing it in the broader range of the field for code generation and debugging.
What can OpenAI: gpt-oss-20b do?
OpenAI: gpt-oss-20b supports tool use and function calling.
Who created OpenAI: gpt-oss-20b?
OpenAI: gpt-oss-20b is developed by OpenAI and was released on August 5, 2025.