gpt-oss-120b model profile

Profile facts

Profile type

Model research profile

Provider or publisher

OpenAI

Context window

131,072 tokens

Snapshot date

2026-09-06

Knowledge cutoff

2024-06-30

Reference catalog ID

openai/gpt-oss-120b

When to pick gpt-oss-120b

gpt-oss-120b is a reference profile: OpenAI publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.

• Reach for it when cost is the binding constraint. At $0.03 in and $0.17 out per 1M tokens, combined token price sits in the cheapest quarter of the 146 models publishing both rates in this snapshot.
• Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
• Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
• Look elsewhere when the prompt is long. The 131K-token context window is in the bottom quarter of the 163 models publishing a limit. Long documents need chunking or a wider-context route.
• Look elsewhere when the task is hard reasoning. Its 15.6 Artificial Analysis intelligence index is below the median of the 32 models carrying that field. Scores from different suites are not interchangeable, so treat this as one signal rather than a ranking.

Context, modalities, and identity

gpt-oss-120b accepts text and returns text. The snapshot records reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.

Provider or publisher

OpenAI

Context window

131,072 tokens

Maximum output

117,964 tokens

Input modalities

text

Output modalities

text

Knowledge cutoff

2024-06-30

Model overview

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Reference model ID

openai/gpt-oss-120b

Canonical version

openai/gpt-oss-120b

Hugging Face ID

openai/gpt-oss-120b

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters

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_a, top_k, top_logprobs, top_p

• reasoning controls
• structured output
• text generation
• tool calling

Dated pricing snapshot

The dated reference snapshot lists $0.03 input and $0.17 output per million tokens. Cached input is $0.02 per million tokens.

These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.

Price date

2026-09-06

Input

$0.03 per 1M tokens

Cached input

$0.02 per 1M tokens

Output

$0.17 per 1M tokens

Provider routes, performance, and uptime

The snapshot retains 22 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.

Active provider endpoints

15

Best p50 latency

0.17 s

Best p50 throughput

705.5 tok/s

Availability with routing

99.48% over the sampled window

Availability without routing

92.47% over the sampled window

Performance date

2026-09-06

Benchmark evidence and limitations

The 2026-09-06 snapshot includes 3 Artificial Analysis indexes, 6 Design Arena categories, and AutoExacto results for 21 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Intelligence Index

15.6

Coding Index

30.4

Agentic Index

6.3

AutoExacto coverage

21 provider observations over 32 days

AutoExacto provider benchmarks

Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.

Popularity and market context

gpt-oss-120b ranked #34 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Third-party catalog rank

#34

Global market share

Not inferred

Observation date

2026-09-06

Frequently asked questions

Sources and evidence dates

1. gpt-oss-120b third-party catalog record (catalog, checked 2026-09-06)
2. Third-party model catalog methodology (methodology, checked 2026-09-06)
3. OpenAI official model documentation (primary, checked 2026-09-06)
4. Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
5. Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)
6. gpt-oss-120b third-party catalog record (benchmark, checked 2026-09-06)