All models
OpenAI
gpt-oss-120b fastruns locally
openai/gpt-oss-120b
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...
Input / 1M
$0.014
USD per million tokens
Output / 1M
$0.052
USD per million tokens
Est. cost / token
$0.000000023
$0.024 per 1M, 3:1 mix
Context window
131K
max output 66K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →ollama run gpt-oss:120b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 55.4 GB |
| Q3_K_M | fair | 64 GB |
| Q4_K_Mrecommended | good | 79 GB |
| Q5_K_M | very good | 91.3 GB |
| Q6_K | excellent | 105 GB |
| Q8_0 | near-lossless | 134 GB |
| F16 | lossless | 250 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.014 | $0.052 | $0.013 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.014
- Output
- $0.052
- Cached input
- $0.013
- Blended (3:1)
- $0.024
Details
- Company
- OpenAI
- Version
- —
- Family
- GPT
- Released
- 2025-08-05
- Parameters
- 117B (5.1B active)
- Max output
- 66K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 21 min ago