OpenAI: gpt-oss-120b
openai/gpt-oss-120b
Model weightsgpt-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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $0.050 | $0.250 | $0.0500 | 0.26s | 207 tok/s | ||
| $0.090 | $0.360 | -- | 0.26s | 226 tok/s | ||
| $0.150 | $0.600 | $0.0750 | 0.19s | 335 tok/s | ||
| $0.060 | $0.400 | $0.0300 | 0.96s | 103 tok/s | ||
| $0.048 | $0.102 | $0.0430 | 0.65s | 81 tok/s | ||
| $0.140 | $0.950 | -- | 1.63s | 356 tok/s | ||
| $0.150 | $0.600 | $0.0750 | 1.19s | 62 tok/s | ||
| $0.060 | $0.420 | $0.0120 | 0.42s | 41 tok/s | ||
| $0.030 | $0.150 | $0.0300 | 1.14s | 32 tok/s | ||
| $0.037 | $0.170 | $0.0185 | 0.42s | 28 tok/s | ||
| $0.070 | $0.250 | $0.0700 | 0.80s | 119 tok/s | ||
| $0.100 | $0.500 | $0.1000 | 0.15s | 203 tok/s | ||
| $0.030 | $0.187 | $0.0300 | 0.40s | 118 tok/s | ||
| $0.030 | $0.150 | $0.0150 | 0.85s | 47 tok/s | ||
| $0.100 | $0.500 | $0.1000 | 0.17s | 172 tok/s | ||
Fast | $0.150 | $0.750 | -- | 0.34s | 103 tok/s | |
| $0.030 | $0.170 | $0.0300 | 0.30s | 83 tok/s | ||
| $0.150 | $0.600 | -- | 0.36s | 149 tok/s | ||
| $0.150 | $0.600 | $0.1000 | 0.27s | 310 tok/s | ||
| $0.150 | $0.600 | -- | 0.56s | 343 tok/s | ||
| $0.150 | $0.600 | -- | 0.21s | 79 tok/s | ||
| $0.350 | $0.750 | $0.3500 | 0.22s | 593 tok/s | ||
| $0.100 | $0.750 | $0.0550 | 0.50s | 140 tok/s | ||
| $0.030 | $0.180 | $0.0300 | 0.92s | 62 tok/s |
- Input $0.05 / Output $0.25207 tok/s100.00% uptime
- Input $0.09 / Output $0.36226 tok/s72.16% uptime
- Input $0.15 / Output $0.60335 tok/s98.81% uptime
- Input $0.06 / Output $0.40103 tok/s100.00% uptime
- Input $0.048 / Output $0.10281 tok/s100.00% uptime
- Input $0.14 / Output $0.95356 tok/s99.55% uptime
- Input $0.15 / Output $0.6062 tok/s91.95% uptime
- Input $0.06 / Output $0.4241 tok/s100.00% uptime
- Input $0.03 / Output $0.1532 tok/s99.70% uptime
Input $0.037 / Output $0.1728 tok/s100.00% uptime- Input $0.07 / Output $0.25119 tok/s100.00% uptime
- Input $0.10 / Output $0.50203 tok/s98.49% uptime
- Input $0.03 / Output $0.187118 tok/s100.00% uptime
Input $0.03 / Output $0.1547 tok/s99.88% uptime- Input $0.10 / Output $0.50172 tok/s99.45% uptime
- Input $0.15 / Output $0.75103 tok/s100.00% uptimeFast
- Input $0.03 / Output $0.1783 tok/s96.72% uptime
- Input $0.15 / Output $0.60149 tok/s100.00% uptime
- Input $0.15 / Output $0.60310 tok/s99.90% uptime
- Input $0.15 / Output $0.60343 tok/s100.00% uptime
- Input $0.15 / Output $0.6079 tok/s97.61% uptime
- Input $0.35 / Output $0.75593 tok/s100.00% uptime
- Input $0.10 / Output $0.75140 tok/s99.86% uptime
- Input $0.03 / Output $0.1862 tok/s99.32% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
gpt-oss-120b — Price history
| $0.0196 | $0.1493 | 68.4% | 11.5% | ||
| $0.0298 | $0.1698 | 58.3% | 3.1% | ||
| $0.0298 | $0.1862 | 49.9% | 5.4% | ||
| $0.0298 | $0.1492 | 60.0% | 0.6% | ||
| $0.0367 | $0.1690 | 0.8% | 7.1% | ||
| $0.0371 | $0.3993 | 76.2% | 4.2% | ||
| $0.0397 | $0.0894 | 52.7% | 2.7% | ||
| $0.0400 | $0.4182 | 41.0% | 0.0% | ||
| $0.0498 | $0.2491 | 60.0% | 18.4% | ||
| $0.0695 | $0.2479 | 35.2% | 0.1% | ||
| $0.0773 | $0.7493 | 50.4% | 0.4% | ||
| $0.0897 | $0.3589 | 51.9% | 9.1% | ||
| $0.0999 | $0.4995 | 65.4% | 1.3% | ||
| $0.0999 | $0.4996 | 78.4% | 0.8% | ||
| $0.1078 | $0.5990 | 56.1% | 17.4% | ||
| $0.1143 | $0.5989 | 70.9% | 0.3% | ||
| $0.1400 | $0.9495 | 0.0% | 1.0% | ||
| $0.1497 | $0.5995 | 0.0% | 0.0% | ||
Fast | $0.1498 | $0.7489 | 38.8% | 0.6% | |
| $0.1498 | $0.5984 | 0.0% | 0.6% | ||
| $0.1499 | $0.5991 | 46.5% | 0.1% | ||
| $0.1499 | $0.5992 | 0.0% | 0.2% | ||
| $0.3498 | $0.7491 | 69.0% | 14.1% | ||
| $0.0298 | $0.1795 | 31.7% | 1.1% |
- Effective in $0.0196 / Effective out $0.1493Token share11.5%
- Effective in $0.0298 / Effective out $0.1698Token share3.1%
- Effective in $0.0298 / Effective out $0.1862Token share5.4%
- Effective in $0.0298 / Effective out $0.1492Token share0.6%
- Effective in $0.0367 / Effective out $0.1690Token share7.1%
- Effective in $0.0371 / Effective out $0.3993Token share4.2%
- Effective in $0.0397 / Effective out $0.0894Token share2.7%
- Effective in $0.0400 / Effective out $0.4182Token share0.0%
- Effective in $0.0498 / Effective out $0.2491Token share18.4%
- Effective in $0.0695 / Effective out $0.2479Token share0.1%
- Effective in $0.0773 / Effective out $0.7493Token share0.4%
- Effective in $0.0897 / Effective out $0.3589Token share9.1%
- Effective in $0.0999 / Effective out $0.4995Token share1.3%
- Effective in $0.0999 / Effective out $0.4996Token share0.8%
- Effective in $0.1078 / Effective out $0.5990Token share17.4%
- Effective in $0.1143 / Effective out $0.5989Token share0.3%
- Effective in $0.1400 / Effective out $0.9495Token share1.0%
- Effective in $0.1497 / Effective out $0.5995Token share0.0%
- Effective in $0.1498 / Effective out $0.7489FastToken share0.6%
- Effective in $0.1498 / Effective out $0.5984Token share0.6%
- Effective in $0.1499 / Effective out $0.5991Token share0.1%
- Effective in $0.1499 / Effective out $0.5992Token share0.2%
- Effective in $0.3498 / Effective out $0.7491Token share14.1%
- Effective in $0.0298 / Effective out $0.1795Token share1.1%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
P50, best across providers
P50, best provider
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | gpt-oss-120b (High) Intelligence Index | 3.8 |
| Artificial Analysis | gpt-oss-120b (High) Coding Index | 30.4 |
| Artificial Analysis | gpt-oss-120b (High) Agentic Index | 3.7 |
| Artificial Analysis | gpt-oss-120b (High) GPQA Diamond | 78.2% |
| Artificial Analysis | gpt-oss-120b (High) HLE | 19.6% |
| Artificial Analysis | gpt-oss-120b (High) IFBench | 69.0% |
| Artificial Analysis | gpt-oss-120b (High) τ²-Bench Telecom | 65.8% |
| Artificial Analysis | gpt-oss-120b (High) AA-LCR | 52.0% |
| Artificial Analysis | gpt-oss-120b (High) τ-Bench Banking | 12.8% |
| Artificial Analysis | gpt-oss-120b (High) GDPval-AA | 5.8% |
| Artificial Analysis | gpt-oss-120b (High) CritPt | 1.1% |
| Artificial Analysis | gpt-oss-120b (High) LiveCodeBench | 87.8% |
| Artificial Analysis | gpt-oss-120b (High) SciCode | 34.0% |
| Artificial Analysis | gpt-oss-120b (High) Terminal-Bench Hard | 23.5% |
| Artificial Analysis | gpt-oss-120b (High) Terminal-Bench 4.0 | 0.0% |
| Artificial Analysis | gpt-oss-120b (High) Terminal-Bench 2.1 | 26.2% |
| Artificial Analysis | gpt-oss-120b (High) MMLU-Pro | 80.8% |
| Artificial Analysis | gpt-oss-120b (High) AA-Omniscience Accuracy | 21.7% |
| Artificial Analysis | gpt-oss-120b (High) AA-Omniscience Non-Hallucination Rate | 13.1% |
| Artificial Analysis | gpt-oss-120b (High) AIME 2025 | 93.4% |
| Artificial Analysis | gpt-oss-120b (Low) Coding Index | 21.2 |
| Artificial Analysis | gpt-oss-120b (Low) GPQA Diamond | 67.2% |
| Artificial Analysis | gpt-oss-120b (Low) HLE | 5.9% |
| Artificial Analysis | gpt-oss-120b (Low) IFBench | 58.3% |
| Artificial Analysis | gpt-oss-120b (Low) τ²-Bench Telecom | 45.0% |
| Artificial Analysis | gpt-oss-120b (Low) AA-LCR | 46.0% |
| Artificial Analysis | gpt-oss-120b (Low) τ-Bench Banking | 2.9% |
| Artificial Analysis | gpt-oss-120b (Low) GDPval-AA | 0.0% |
| Artificial Analysis | gpt-oss-120b (Low) CritPt | 0.0% |
| Artificial Analysis | gpt-oss-120b (Low) LiveCodeBench | 70.7% |
| Artificial Analysis | gpt-oss-120b (Low) Terminal-Bench Hard | 5.3% |
| Artificial Analysis | gpt-oss-120b (Low) Terminal-Bench 2.1 | 13.9% |
| Artificial Analysis | gpt-oss-120b (Low) MMLU-Pro | 77.5% |
| Artificial Analysis | gpt-oss-120b (Low) AIME 2025 | 66.7% |
| Design Arena | GPT OSS 120B Models Arena 3D Elo | 881 |
| Design Arena | GPT OSS 120B Models Arena Code Categories Elo | 952 |
| Design Arena | GPT OSS 120B Models Arena Data Visualization Elo | 984 |
| Design Arena | GPT OSS 120B Models Arena Game Development Elo | 981 |
| Design Arena | GPT OSS 120B Models Arena UI Component Elo | 915 |
| Design Arena | GPT OSS 120B Models Arena Website Elo | 960 |
| Vals AI | GPT OSS 120B AIME | 92.6% |
| Vals AI | GPT OSS 120B CaseLaw v2 | 48.8% |
| Vals AI | GPT OSS 120B CorpFin v2 | 58.2% |
| Vals AI | GPT OSS 120B Finance Agent v1.1 | 21.5% |
| Vals AI | GPT OSS 120B GPQA Diamond | 78.5% |
| Vals AI | GPT OSS 120B LiveCodeBench | 83.2% |
| Vals AI | GPT OSS 120B LegalBench | 75.9% |
| Vals AI | GPT OSS 120B MATH 500 | 94.8% |
| Vals AI | GPT OSS 120B MedQA | 91.4% |
| Vals AI | GPT OSS 120B MGSM | 92.0% |
| Vals AI | GPT OSS 120B MMLU Pro | 79.2% |
| Vals AI | GPT OSS 120B SWE-bench | 33.6% |
| Vals AI | GPT OSS 120B TaxEval v2 | 71.6% |
| Vals AI | GPT OSS 120B Terminal-Bench 2.0 | 19.1% |
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Available through EU in-region routing
OpenAI: gpt-oss-120b is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).
- Providers in Europe
- Amazon Bedrock
- Prices in Europe
- Amazon Bedrock: $0.15/M tokens input, $0.60/M tokens output
- Base URL
https://eu.openrouter.ai/api/v1- Plan
- Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing
Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with OpenAI: gpt-oss-120b on OpenRouter.
Frequently asked questions
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 to run on a single H100 GPU with native MXFP4 quantization.
The gpt-oss-120b documentation on OpenRouter includes the LLM Quantization: What fp8 and fp4 Do to Quality and Price blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
gpt-oss-120b costs $0.03/M input tokens and $0.15/M output tokens, with separate rates for Cache Read at $0.015/M tokens.
gpt-oss-120b has a 131,072 token context window. It supports up to 131,072 completion tokens.
Yes. gpt-oss-120b accepts tools and tool_choice for function calling on 18 of the 21 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.
gpt-oss-120b is served by 21 providers on OpenRouter: NEAR AI, Venice, CoreWeave, DekaLLM, AkashML, DeepInfra, Prime Intellect, Crusoe and 13 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
gpt-oss-120b was released on August 5, 2025. Its knowledge cutoff is June 30, 2024.