gpt-oss-120b
The 33rd most-used model on the router over the last 7 days, with 0.38% of tokens. Weekly share peaked at 5.6% in the week of Dec 8, 2025, with 18T tokens processed since Aug 4, 2025.
- Launch
- Aug 5, 2025
- Context
- 128k tokens
- Modality
- text → text
- Reasoning
- yes
- License
- Open weights
- Input
- $0.037 / 1M
- Output
- $0.17 / 1M
Weekly token share
Share of the router's weekly volume, since the first week with volume
See the numbers
| Week | Share |
|---|---|
| Aug 31, 2026 | 0.400% |
| Aug 24, 2026 | 0.418% |
| Aug 17, 2026 | 0.553% |
| Aug 10, 2026 | 0.588% |
| Aug 3, 2026 | 0.606% |
| Jul 27, 2026 | 0.956% |
| Jul 20, 2026 | 0.810% |
| Jul 13, 2026 | 0.842% |
| Jul 6, 2026 | 0.987% |
| Jun 29, 2026 | 1.006% |
| Jun 22, 2026 | 1.175% |
| Jun 15, 2026 | 1.240% |
| Jun 8, 2026 | 1.414% |
| Jun 1, 2026 | 1.680% |
| May 25, 2026 | 1.828% |
| May 18, 2026 | 1.933% |
| May 11, 2026 | 2.062% |
| May 4, 2026 | 2.052% |
| Apr 27, 2026 | 2.091% |
| Apr 20, 2026 | 2.186% |
| Apr 13, 2026 | 2.323% |
| Apr 6, 2026 | 1.972% |
| Mar 30, 2026 | 1.609% |
| Mar 23, 2026 | 2.033% |
| Mar 16, 2026 | 2.016% |
| Mar 9, 2026 | 2.453% |
| Mar 2, 2026 | 3.359% |
| Feb 23, 2026 | 2.466% |
| Feb 16, 2026 | 2.235% |
| Feb 9, 2026 | 2.458% |
| Feb 2, 2026 | 2.643% |
| Jan 26, 2026 | 3.690% |
| Jan 19, 2026 | 3.492% |
| Jan 12, 2026 | 2.995% |
| Jan 5, 2026 | 1.889% |
| Dec 29, 2025 | 1.972% |
| Dec 22, 2025 | 1.950% |
| Dec 15, 2025 | 3.771% |
| Dec 8, 2025 | 5.596% |
| Dec 1, 2025 | 2.291% |
| Nov 24, 2025 | 1.024% |
| Nov 17, 2025 | 1.019% |
| Nov 10, 2025 | 0.893% |
| Nov 3, 2025 | 1.213% |
| Oct 27, 2025 | 1.292% |
| Oct 20, 2025 | 1.697% |
| Oct 13, 2025 | 1.665% |
| Oct 6, 2025 | 1.400% |
| Sep 29, 2025 | 1.300% |
| Sep 22, 2025 | 0.954% |
| Sep 15, 2025 | 1.008% |
| Sep 8, 2025 | 1.887% |
| Sep 1, 2025 | 0.768% |
| Aug 25, 2025 | 1.460% |
| Aug 18, 2025 | 1.466% |
| Aug 11, 2025 | 1.620% |
| Aug 4, 2025 | 1.398% |
Debuted in the week of Aug 4, 2025 and peaked at 5.6% 18 weeks later. The latest full week came in at 0.40%, 7% of peak.
What this model is used for new
Tasks where the model ranks among the leaders, and its share of each
Ranks among the leaders in 8 of the 29 classified tasks. Its largest share is in summarization, 2.7% of the task's tokens; in the heaviest task where it appears, classification (5.4% of classified volume), it holds 2.3%.
Snapshot of the rolling 7-day window through Sep 10, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.
Where to run it
Endpoints in the source's catalog, from cheapest to most expensive on input
| Provider | Input | Output | Context | Quantization | Zero retention |
|---|---|---|---|---|---|
| AkashML | $0.03 | $0.17 | 128k | bf16 | yes |
| CoreWeave | $0.03 | $0.17 | 128k | fp4 | yes |
| DekaLLM | $0.03 | $0.18 | 128k | bf16 | no |
| DeepInfra | $0.037 | $0.17 | 128k | bf16 | yes |
| Novita | $0.05 | $0.25 | 128k | fp4 | yes |
| DigitalOcean | $0.055 | $0.385 | 125k | not reported | yes |
| Mancer 2 | $0.055 | $0.50 | 128k | fp8 | yes |
| $0.09 | $0.36 | 128k | not reported | yes | |
| BaseTen | $0.10 | $0.50 | 125k | fp4 | yes |
| BaseTen | $0.10 | $0.50 | 125k | fp4 | yes |
| Parasail | $0.10 | $0.75 | 128k | fp4 | yes |
| SambaNova | $0.14 | $0.95 | 128k | not reported | yes |
| Amazon Bedrock | $0.15 | $0.60 | 128k | not reported | yes |
| Nebius | $0.15 | $0.60 | 128k | fp4 | yes |
| Amazon Bedrock | $0.15 | $0.60 | 128k | not reported | yes |
| DeepInfra | $0.15 | $0.60 | 128k | bf16 | yes |
| SiliconFlow | $0.15 | $0.60 | 128k | fp8 | yes |
| Phala | $0.15 | $0.60 | 128k | not reported | yes |
| Together | $0.15 | $0.60 | 128k | not reported | yes |
| Groq | $0.15 | $0.60 | 128k | not reported | yes |
| Mara | $0.15 | $0.75 | 128k | not reported | yes |
| DeepInfra | $0.20 | $0.95 | 128k | fp8 | yes |
| Cerebras | $0.35 | $0.75 | 128k | fp16 | yes |
23 endpoints across 19 providers, with input from $0.03 to $0.35 per 1M tokens. 22 offer zero data retention.
Prices in US dollars per million tokens, from the latest archived endpoint catalog.
Benchmarks
Artificial Analysis indexes and benchmarks run by the source, with cost per task
GPQA Diamond 75.1%
$0.007 per task, 4353 tasks. 85th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.
τ-bench verified, airline 64.4%
$0.013 per task, 1448 tasks. 78th of 122 evaluated. Median of evaluated models: 70.7%, $0.056 per task.
Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 11, 2026. The gray mark is the median of evaluated models.
Against the week's largest models
The five largest proprietary and five largest open-weights models over the last 7 days
| Model | Lab | 7-day share | Blended price | Context | Intelligence | Weeks in top 10 |
|---|---|---|---|---|---|---|
| Proprietary | ||||||
| GPT-5.6 LunaOpenAI | OpenAI | 11.5% | $0.45 | 1M | 37.5 | 6 |
| Gemini 3.8 FlashGoogle | 2.1% | $1.50 | 1M | 41.2 | 0 | |
| Muse Spark 1.3 ContributorMeta | Meta | 1.5% | $0.125 | 1M | — | 0 |
| Claude Opus 5Anthropic | Anthropic | 1.4% | $10.00 | 1M | 50.7 | 1 |
| GPT-5.6 SolOpenAI | OpenAI | 1.4% | $4.00 | 1M | 47.1 | 0 |
| Open weights | ||||||
| Hy4 previewTencent | Tencent | 15.5% | $1.25 | 1M | — | 1 |
| DeepSeek V4 Flash 0731DeepSeek | DeepSeek | 10.0% | $0.094 | 1.31M | 34.5 | 5 |
| GLM 5.3 FlashZ.ai (GLM) | Z.ai (GLM) | 10.0% | $0.237 | 1.31M | 41.9 | 2 |
| MiMo-V2.5Xiaomi | Xiaomi | 4.2% | $0.175 | 1M | 22.3 | 15 |
| DeepSeek V4 Flash 0423DeepSeek | DeepSeek | 3.9% | $0.111 | 1M | 24.8 | 19 |
| gpt-oss-120bthis pageOpenAI | OpenAI | 0.38% | $0.07 | 128k | 12.3 | 5 |
Share over the last 7 days (Sep 4, 2026 to Sep 10, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.