Baltor Get started

Models

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

Each provider's own price in US dollars per million tokens, as an openly licensed source lists it
ProviderInputOutputContextAs ofSource
Kilo Gateway0.030 USD0.150 USD131,072 older than 30 days; check the providermodels.dev, read
NanoGPT0.030 USD0.150 USD128,000 older than 30 days; check the providermodels.dev, read
CoreWeave0.030 USD0.170 USD131,072 older than 30 days; check the providermodels.dev, read
OrcaRouter0.030 USD0.170 USD131,072 older than 30 days; check the providermodels.dev, read
Deep Infra0.037 USD0.170 USD131,072 older than 30 days; check the providermodels.dev, read
IO.NET0.040 USD0.400 USD131,072 older than 30 days; check the providermodels.dev, read
Crusoe0.050 USD0.200 USD131,072 older than 30 days; check the providermodels.dev, read
Merge Gateway0.050 USD0.250 USD128,000 older than 30 days; check the providermodels.dev, read
Novita AI0.050 USD0.250 USD131,072 older than 30 days; check the providermodels.dev, read
SiliconFlow0.050 USD0.450 USD131,000 older than 30 days; check the providermodels.dev, read
sail0.060 USD0.400 USD131,072LiteLLM, read
Abacus0.080 USD0.440 USD128,000 older than 30 days; check the providermodels.dev, read
Baseten0.100 USD0.500 USD128,072 older than 30 days; check the providermodels.dev, read
Vercel AI Gateway0.100 USD0.500 USD131,072 older than 30 days; check the providermodels.dev, read
submodel0.100 USD0.500 USD131,072 older than 30 days; check the providermodels.dev, read
OpenReason0.105 USD0.422 USD131,072 older than 30 days; check the providermodels.dev, read
FastRouter0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
Groq0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
Nebius Token Factory0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
OpenRouter0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
Pioneer0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
Scaleway0.150 USD0.600 USD128,000LiteLLM, read
Together AI0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
ai&0.150 USD0.600 USD131,072 older than 30 days; check the providermodels.dev, read
tensormesh0.150 USD0.600 USD131,072LiteLLM, read
watsonx.ai0.159 USD0.636 USD131,072 older than 30 days; check the providermodels.dev, read
replicate0.180 USD0.720 USDUnknownLiteLLM, read
inferenceapis0.200 USD0.800 USD131,072LiteLLM, read
evroc0.230 USD0.920 USD65,536 older than 30 days; check the providermodels.dev, read
Hugging Face0.250 USD0.690 USD131,072 older than 30 days; check the providermodels.dev, read
Prime Inference0.350 USD0.750 USD131,072 older than 30 days; check the providermodels.dev, read
AI/ML API0.481 USD1.31 USD131,000 older than 30 days; check the providermodels.dev, read
STACKIT0.530 USD0.760 USD131,000 older than 30 days; check the providermodels.dev, read
CloudFerro Sherlock2.92 USD2.92 USD131,000 older than 30 days; check the providermodels.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.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
MXFP459.0 GiB63.0 GiB64.7 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

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

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.