gpt-oss-120b
By openai. 116.8 billion parameters, a context window of 131,072 tokens and the licence apache-2.0.
Facts
- Released
- 2025-08-04 the day the repository was first published on Hugging Face Hugging Face, read
- Licence
- apache-2.0 the licence the model card declares Hugging Face, read
- Open weights
- Yes the weights are published in this Hugging Face repository Hugging Face, read
- Parameters
- 116.8 billion counted from the safetensors weight files Hugging Face, read
- Active parameters
- 5.8 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
- Knowledge cutoff
- Unknown
- Context window
- 131,072 tokens the maximum position embeddings in the model configuration model configuration, read
- Longest output
- Unknown
- Tool calling
- Unknown
- Structured output
- Unknown
- Reasoning controls
- Unknown
- Inputs and outputs
- text in, text out Hugging Face, read
- Good for
- No source names a use.
Prices
| Provider | Input | Output | Context | As of | Source |
|---|---|---|---|---|---|
| Kilo Gateway | 0.030 USD | 0.150 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| NanoGPT | 0.030 USD | 0.150 USD | 128,000 | older than 30 days; check the provider | models.dev, read |
| CoreWeave | 0.030 USD | 0.170 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| OrcaRouter | 0.030 USD | 0.170 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Deep Infra | 0.037 USD | 0.170 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| IO.NET | 0.040 USD | 0.400 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Crusoe | 0.050 USD | 0.200 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Merge Gateway | 0.050 USD | 0.250 USD | 128,000 | older than 30 days; check the provider | models.dev, read |
| Novita AI | 0.050 USD | 0.250 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| SiliconFlow | 0.050 USD | 0.450 USD | 131,000 | older than 30 days; check the provider | models.dev, read |
| sail | 0.060 USD | 0.400 USD | 131,072 | LiteLLM, read | |
| Abacus | 0.080 USD | 0.440 USD | 128,000 | older than 30 days; check the provider | models.dev, read |
| Baseten | 0.100 USD | 0.500 USD | 128,072 | older than 30 days; check the provider | models.dev, read |
| Vercel AI Gateway | 0.100 USD | 0.500 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| submodel | 0.100 USD | 0.500 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| OpenReason | 0.105 USD | 0.422 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| FastRouter | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Groq | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Nebius Token Factory | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| OpenRouter | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Pioneer | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Scaleway | 0.150 USD | 0.600 USD | 128,000 | LiteLLM, read | |
| Together AI | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| ai& | 0.150 USD | 0.600 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| tensormesh | 0.150 USD | 0.600 USD | 131,072 | LiteLLM, read | |
| watsonx.ai | 0.159 USD | 0.636 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| replicate | 0.180 USD | 0.720 USD | Unknown | LiteLLM, read | |
| inferenceapis | 0.200 USD | 0.800 USD | 131,072 | LiteLLM, read | |
| evroc | 0.230 USD | 0.920 USD | 65,536 | older than 30 days; check the provider | models.dev, read |
| Hugging Face | 0.250 USD | 0.690 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| Prime Inference | 0.350 USD | 0.750 USD | 131,072 | older than 30 days; check the provider | models.dev, read |
| AI/ML API | 0.481 USD | 1.31 USD | 131,000 | older than 30 days; check the provider | models.dev, read |
| STACKIT | 0.530 USD | 0.760 USD | 131,000 | older than 30 days; check the provider | models.dev, read |
| CloudFerro Sherlock | 2.92 USD | 2.92 USD | 131,000 | older than 30 days; check the provider | models.dev, read |
Run it on your own hardware
Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.
| Quantization | Weights | Memory at 8,192 tokens | Memory at 32,768 tokens |
|---|---|---|---|
| MXFP4 | 59.0 GiB | 63.0 GiB | 64.7 GiB |
Start it with a local runtime
- Ollama
ollama run hf.co/ggml-org/gpt-oss-120b-GGUF:MXFP4 - LM Studio
lms get ggml-org/gpt-oss-120b-GGUF lms server start - llama.cpp server
llama-server -hf ggml-org/gpt-oss-120b-GGUF:MXFP4 --jinja - vLLM
vllm serve openai/gpt-oss-120b - SGLang
sglang serve --model-path openai/gpt-oss-120b --port 30000
Use it from your harness
Set up for Abacus with the model openai/gpt-oss-120b. Each endpoint page has the same setup for its own address.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"abacus": {
"npm": "@ai-sdk/openai-compatible",
"name": "Abacus",
"options": {
"baseURL": "https://routellm.abacus.ai/v1",
"apiKey": "{env:ABACUS_API_KEY}"
},
"models": {
"openai/gpt-oss-120b": {
"name": "gpt-oss-120b"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"abacus": {
"baseUrl": "https://routellm.abacus.ai/v1",
"api": "openai-completions",
"apiKey": "$ABACUS_API_KEY",
"models": [
{
"id": "openai/gpt-oss-120b"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and Abacus documents no Responses address. A gateway that offers one can sit in between.
- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and Abacus documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Other ways to reach it
- ai&, model
openai/gpt-oss-120b - AI/ML API, model
openai/gpt-oss-120b - Baseten, model
openai/gpt-oss-120b - CloudFerro Sherlock, model
openai/gpt-oss-120b - Crusoe, model
openai/gpt-oss-120b - DeepInfra, model
openai/gpt-oss-120b - evroc, model
openai/gpt-oss-120b - FastRouter, model
openai/gpt-oss-120b - Groq, model
openai/gpt-oss-120b - Hugging Face, model
openai/gpt-oss-120b - IO.NET, model
openai/gpt-oss-120b
Published results
These are results other people published. Baltor did not run them and does not rank models by them.
- Results the maker published on the model card published by openai Hugging Face, read
Two more publishers are linked, never copied, because their terms do not allow it:
- Artificial Analysis publishes its own intelligence, speed and price measurements.
- OpenRouter lists current prices and uptime for each provider it routes to.
Sources of this page
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.