xpu liveBETA
Models›gpt-oss-20b

gpt-oss-20b

Model reference ↗

Model ranking

Arena Score
1287.5645926246
Arena reference rank
269
Evaluation configuration
gpt-oss-20b
Source published
2026-11-19
Votes
10393
Confidence lower
1281.1691800134
Confidence upper
1293.9600052359
Last successful check
2026-11-22T14:00:05.877Z
Last value/rank change
2026-11-22T09:30:20.053Z
Methodology
Human preference — Text / overall; checked every six hours.

Source: Arena / LMArena ↗ · CC BY 4.0. Selection and catalog matching by XPU LIVE.

Pricing 3 Model information

Provider prices 3

Lowest input price per billing unit. Conditions in Details.

ProviderPriceProvider model IDStatusContext / max outputSource
OpenRouter
Batch / Router catalog
Input $0.024USD / 1M tokensOutput $0.112USD / 1M tokens
Updated 2026-11-22 · 15:43 UTC
openai/gpt-oss-20bCatalog-listed
Conditions

Catalog-listed; account access and regional availability may apply.

Context tokens 131072Output tokens 32768Official source ↗2026-09-28
Groq
Standard
Input $0.075USD / 1M tokensOutput $0.3USD / 1M tokens
Updated 2026-11-22 · 15:43 UTC
openai/gpt-oss-20bCatalog-listed
Conditions

Catalog-listed; account access and regional availability may apply.

Context tokens 131072Output tokens 65536Official source ↗2026-09-28
Cloudflare Workers AIgpt-oss-20b
Standard
Input $0.2USD / 1M tokensOutput $0.3USD / 1M tokens
Updated 2026-11-22 · 15:43 UTC
@cf/openai/gpt-oss-20bCatalog-listed
Conditions

Public catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine.

Context tokens 128000Official source ↗2026-10-20

OpenAI’s smaller gpt-oss model offers open-weight text reasoning in a more compact mixture-of-experts checkpoint. It belongs to the same family as gpt-oss-120b but is a distinct model size.

gpt-oss-20b: suitable applications

Use it for text assistants, bounded analytical questions and tool-assisted workflows where a smaller model is worth evaluating before adopting a larger deployment.

Capabilities and technical details

The model combines instruction following with configurable reasoning. Public weights make it possible to compare hosted behavior with a compatible local runtime.

gpt-oss-20b accepts text and returns text. The recorded input reference is 131,072 tokens, with any lower Cloudflare cap recorded separately. The recorded terms are Apache 2.0; the linked source explains their scope.

gpt-oss-20b limitations and selection

It does not directly transcribe audio or interpret images. Smaller size is not proof of lower end-to-end latency on a particular hosted service.

Include difficult failure cases in an evaluation against gpt-oss-120b, and compare total input and output charges rather than parameter count alone.

gpt-oss-20b API pricing

gpt-oss-20b pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.

Review the Cloudflare gpt-oss-20b endpoint reference and the OpenAI model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.

CONTEXT TOKENS131,072Developer documentation
MAX OUTPUT TOKENS131,072Developer documentation
PROVIDERS3Linked in this catalog
SOURCE CHECKED2026-10-20Sources reviewed; unknown fields labeled

Specifications

Catalog model ID
openai/gpt-oss-20b
Developer model ID / revision
gpt-oss-20bDeveloper documentation ↗
Context / input token limit
131,072Developer model card / documentation ↗
Maximum output tokens
131,072Developer documentation ↗
Structured output
SupportedDeveloper documentation ↗
API parameters (source-specific)
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_pOpenRouter catalog ↗
API parameter scope
OpenRouter API; support varies by route
Weight license / access terms
Apache 2.0Developer weight license / hosted access terms ↗
Total parameters (billions)
21Developer model card / documentation ↗
Active parameters (billions)
3.6Developer model card / documentation ↗
Parameter-count details
Developer-declared nominal model size; serialized tensor counts can differ. Active parameters, when supplied, are separate from total parameters.Developer model card ↗
Download size (GB)
Depends on checkpoint and precision; no verified file size
Release date
Not verified in cited sources
Added to OpenRouter
2025-08-05OpenRouter catalog ↗
Notes
Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Context shown here is the publisher configuration; provider caps can be lower. Parameter sizes are developer-declared nominal labels; serialized tensor counts may differ.

Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.