gpt-oss
gpt-oss is a series of open-weight language models from OpenAI that the README describes as designed for reasoning, agentic tasks and developer use cases, released in two variants.
- Verified facts
- 7
- Offers
- 1
- Sources
- 1
- Pricing
- Free offer
Overview
What gpt-oss covers
gpt-oss is a series of open-weight language models from OpenAI. The README describes them as designed for reasoning, agentic tasks and developer use cases, and lists two variants: gpt-oss-120b, with 117B parameters and 5.1B active, which it says fits a single 80GB GPU, and gpt-oss-20b, with 21B parameters and 3.6B active, for lower latency and local or specialized use.
The README lists configurable reasoning effort (low, medium, high), access to the full chain-of-thought, fine-tuning, function calling, web browsing, Python code execution and structured outputs.
Read the full editorial overview
Licence and running it
The repository licence file is the Apache License, Version 2.0, and the README highlights a permissive Apache 2.0 license. The README shows inference through Transformers and vLLM and describes reference PyTorch, Triton and Metal implementations.
It says MXFP4 quantization lets gpt-oss-120b run on a single 80GB GPU and gpt-oss-20b run within 16GB of memory, and that both models must be used with the harmony response format. The README does not discuss pricing.
Maintenance and what is not established
This capture follows release v0.0.9, published on 13 January 2026. The default branch has a commit dated 29 October 2026 and the repository is not archived.
Nothing was installed, run or benchmarked, so hardware figures, quality and tool behavior are the project's own statements. The README gives no model context length; only its terminal chat example has a default of 8192.
Sources
gpt-oss: gpt-oss-project · Evidence: documentation · Not checked
Plans & prices
Prices as listed by gpt-oss, before any tax or fee the pricing page does not state.
Scroll the table sideways for every column.
| Plan | Rate period not stated | Coverage limits |
|---|---|---|
| Plan: Self-hosted | FreeTax: Confirm at checkoutUpfront: not established ConditionsPublisher project README at tag v0.0.9 (commit 5994767) captured 9 November 2026; supplier description, not a deployment, inference or independent test. The README highlights a permissive Apache 2.0 license for the open-weight models for experimentation, customization and commercial deployment. Applies to the downloaded open weights run on your own infrastructure; hardware, hosting, OpenAI-hosted or other managed offerings are priced separately and are not covered here. | gpt-oss-120b is described as fitting a single 80GB GPU (such as NVIDIA H100 or AMD MI300X) and gpt-oss-20b as running within 16GB of memory, using the MXFP4 quantization the models were post-trained with.ConditionsPublisher project README at tag v0.0.9 (commit 5994767) captured 9 November 2026; supplier description, not a deployment, inference or independent test. Stated memory targets, not a capacity or performance test. The README's own PyTorch, Triton and Metal implementations are reference code not expected to run in production; Ollama, LM Studio, vLLM and Transformers are listed for running the models. |
Documented facts
Each fact comes from official documentation and shows when it was verified.
Who it is for
gpt-oss is a series of open-weight language models from OpenAI that the README describes as designed for reasoning, agentic tasks and developer use cases, released in two variants.
Coverage limits
Per the README, both gpt-oss models were trained with the harmony response format and should only be used with that format, otherwise they will not work correctly.
Provider
OpenAI
Publisher project README at tag v0.0.9 (commit 5994767) captured 9 November 2026; supplier description, not a deployment, inference or independent test. The README calls gpt-oss OpenAI's open-weight models.
API model identifier
gpt-oss-120b and gpt-oss-20b
Publisher project README at tag v0.0.9 (commit 5994767) captured 9 November 2026; supplier description, not a deployment, inference or independent test. The two released models; Hugging Face repositories are openai/gpt-oss-120b and openai/gpt-oss-20b.
Availability
Model weights can be downloaded from the Hugging Face Hub (openai/gpt-oss-120b and openai/gpt-oss-20b).
Publisher project README at tag v0.0.9 (commit 5994767) captured 9 November 2026; supplier description, not a deployment, inference or independent test. Download instruction, not a statement of current hosted availability or of any OpenAI-hosted service. Licence is covered by the separate pricing fact.
Applies to the facts above: Dated publisher project README captured on 7 November 2026; supplier description, not a deployment or independent test. Infrastructure, accounts, third-party services and managed offerings have separate costs and terms.
Not confirmed in our sources
We have not confirmed these terms for gpt-oss in the linked documentation. That does not mean gpt-oss lacks them; confirm them before you rely on them.
- Modalities
- Context window
- Maximum output
- Input token rate
- Output token rate
Sources & methodology
Facts come from the linked documentation. Documentation checks are not hands-on tests, and readable sources can have incomplete coverage.
Discovered an undocumented discrepancy or pricing shift? Submit a correction request.
Submit correctiongpt-oss alternatives
Other AI models tools to weigh. Different billing units do not establish a cost winner, so compare plans side by side.
GPT-6.1 Sol
AI models
An OpenAI model accepting text and images and producing text. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Claude Sonnet 5.5
AI models
An Anthropic Claude model with text and image inputs and text output. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Gemini 3.8 Flash
AI models
A Google Gemini model accepting text, images, video, audio and PDFs, with text output. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
gpt-oss comparisons
Compare two products in the same category using their documented terms and sources.
- gpt-oss vs Claude Sonnet 5.5
- gpt-oss vs DeepSeek V3
- gpt-oss vs Gemini 3.8 Flash
- gpt-oss vs GLM-4.5
- gpt-oss vs GLM-5 series
- gpt-oss vs GPT-6.1 Sol
- gpt-oss vs IBM Granite 4.1 Language Models
- gpt-oss vs InternLM3
- gpt-oss vs Intern-S series
- gpt-oss vs Kimi K2
- gpt-oss vs LongCat-Flash-Chat
- gpt-oss vs Microsoft Phi-4
- gpt-oss vs MiMo-V2-Flash
- gpt-oss vs MiniCPM
- gpt-oss vs OLMo-2-1124-7B-Instruct
- gpt-oss vs Qwen3-8B
- gpt-oss vs Qwen3-VL
- gpt-oss vs SmolLM
- gpt-oss vs Step 3.5 Flash