| Provider | OpenAI |
|---|---|
| Model ID | openai/gpt-oss-120b |
| Prompt Price per 1M tokens | $0.03 |
| Completion Price per 1M tokens | $0.15 |
| Sample Workload Cost 1M input + 500K output | $0.1 |
| Context Window | 131.07K |
| Release Date | |
| Popularity | #22 |
| Popularity Signal | 59.5B tokens |
gpt-oss-120b
OpenAI API model specs with normalized input price, output price, context window, sample workload cost, and related comparisons.
Page updated:
Data confirmed:
Prices normalized to USD per 1M tokens
Sample workload: 1M input + 500K output
Budget brief
gpt-oss-120b is estimated at $0.1 for the standard workload.
gpt-oss-120b is best suited for cost-sensitive production traffic. A 1M input token plus 500K output token workload is estimated at $0.1.
Input price$0.03per 1M tokens
Output price$0.15per 1M tokens
Context window131.07Kreported maximum
Popularity#2259.5B tokens signal volume
Use this as a first-pass planning estimate, then verify provider limits, routing, discounts, and availability before production deployment.
Estimate your workload cost
Estimate this model for your workload
This estimate uses normalized public API pricing per 1M tokens. It is a planning aid, not a billing quote. Verify provider pricing, limits, and terms before production use.
Alternative path
Alternative Shortlist
Use these rows to build a test shortlist around gpt-oss-120b. Lower cost, same-provider fit, and larger context are separate decisions, so each group is ranked by a different signal.
Lower-cost alternatives
Cross-provider candidates with a lower standard 1M input plus 500K output estimate.
| Model | Provider | Sample Cost | Context | Why it is here | Next Step |
|---|---|---|---|---|---|
| 🔥Owl Alpha | OpenRouter | $0 | 1.05M | Lower standard workload estimate from another provider. | Open model Compare |
| New🔥Nemotron 3 Ultra (free) | NVIDIA | $0 | 1M | Lower standard workload estimate from another provider. | Open model Compare |
| 🔥Laguna M.1 (free) | Poolside | $0 | 262.14K | Lower standard workload estimate from another provider. | Open model Compare |
| Nemotron 3 Super (free) | NVIDIA | $0 | 1M | Lower standard workload estimate from another provider. | Open model Compare |
Same-provider swaps
Lower-cost options from the same provider, useful when account setup or procurement is already fixed.
| Model | Provider | Sample Cost | Context | Why it is here | Next Step |
|---|---|---|---|---|---|
| gpt-oss-120b (free) | OpenAI | $0 | 131.07K | Same provider with a lower standard workload estimate. | Open model Compare |
| gpt-oss-20b (free) | OpenAI | $0 | 131.07K | Same provider with a lower standard workload estimate. | Open model Compare |
| gpt-oss-20b | OpenAI | $0.1 | 131.07K | Same provider with a lower standard workload estimate. | Open model Compare |
Larger-context upgrades near this budget
Models with more context that stay within a close sample-cost band when price data is available.
| Model | Provider | Sample Cost | Context | Why it is here | Next Step |
|---|---|---|---|---|---|
| 🔥Owl Alpha | OpenRouter | $0 | 1.05M | More context while staying near this model's sample-cost band. | Open model Compare |
| Lyria 3 Pro Preview | $0 | 1.05M | More context while staying near this model's sample-cost band. | Open model Compare | |
| Lyria 3 Clip Preview | $0 | 1.05M | More context while staying near this model's sample-cost band. | Open model Compare | |
| DeepSeek V4 Flash (free) | DeepSeek | $0 | 1.05M | More context while staying near this model's sample-cost band. | Open model Compare |
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...
gpt-oss-120b is best suited for cost-sensitive production traffic.
A 1M input token plus 500K output token workload is estimated at $0.1.
Decision Shortcuts
Compare this model
Search head-to-head pages that include gpt-oss-120b and review input price, output price, context, and sample workload cost.
Find comparisonsOpenAI catalog
See other OpenAI models before narrowing your shortlist.
Open provider hubCheaper alternatives
Start from models sorted by a standard cost estimate when budget is the first constraint.
Browse low-cost modelsLong-context alternatives
Compare large-context models for retrieval, documents, and codebase review.
Browse long-context modelsHigh-Interest Comparisons
Search this model| Comparison | Cost-first Pick | Context Pick |
|---|---|---|
| gpt-oss-120b vs Qwen3.5-122B-A10B | gpt-oss-120b | Qwen3.5-122B-A10B |
| gpt-oss-120b vs Laguna XS.2 (free) | Laguna XS.2 (free) | Laguna XS.2 (free) |
| 🔥Laguna M.1 (free) vs gpt-oss-120b | Laguna M.1 (free) | Laguna M.1 (free) |
| gpt-oss-120b vs CoBuddy (free) | CoBuddy (free) | Tie |
| 🔥Claude Opus 4.6 vs gpt-oss-120b | gpt-oss-120b | Claude Opus 4.6 |
| 🔥DeepSeek V4 Flash vs gpt-oss-120b | gpt-oss-120b | DeepSeek V4 Flash |
| Kimi K2.6 vs gpt-oss-120b | gpt-oss-120b | Kimi K2.6 |
| gpt-oss-120b vs Gemma 4 31B | gpt-oss-120b | Gemma 4 31B |
Popular Comparisons
Search all comparisons| Comparison | Newest Release |
|---|---|
| 🔥Claude Opus 4.6 vs gpt-oss-120b | |
| 🔥Claude Opus 4.7 vs gpt-oss-120b | |
| 🔥Claude Sonnet 4.6 vs gpt-oss-120b | |
| 🔥DeepSeek V3.2 vs gpt-oss-120b | |
| 🔥DeepSeek V4 Flash vs gpt-oss-120b | |
| 🔥DeepSeek V4 Pro vs gpt-oss-120b | |
| 🔥Gemini 2.5 Flash Lite vs gpt-oss-120b | |
| 🔥Gemini 2.5 Flash vs gpt-oss-120b | |
| 🔥Gemini 3 Flash Preview vs gpt-oss-120b | |
| 🔥Gemini 3.1 Flash Lite vs gpt-oss-120b |