--- title: "OpenAI: gpt-oss-120b — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/openai__gpt-oss-120b/ description: "OpenAI: gpt-oss-120b: $0.030/M in, $0.170/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # OpenAI: gpt-oss-120b — price, capability and what beats it · Undominated.ai > OpenAI: gpt-oss-120b: $0.030/M in, $0.170/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/openai__gpt-oss-120b/) [Cheaper alternatives](/alternatives/) [Family](/families/gpt-oss/) [Compare models](https://undominated.ai/compare/?models=openai%2Fgpt-oss-120b) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # gpt-oss-120b OpenAI · 05 Aug 2025 · apache-2.0 Balanced Summarise Chat Code gen Agentic FRONTIER ## Nothing is both better and cheaper under this workload. **$0.065** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [Vendor cross-check](https://openrouter.ai/api/v1/models) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,365.4 ± 4.37 · 30,018 votes Context window 131.07K Maximum output 117.96K Input modalities text Output modalities text Published input price $0.030 / 1M tokens Published output price $0.170 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from CoreWeave: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate. Every price dimension · USD per million tokens | Input | $0.030 /M | | --- | --- | | Output | $0.170 /M | | Cached input | $0.030 /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.030/M from DekaLLM. 23 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller DekaLLM dekallm/bf16 Endpoint terms Cached input /M $0.030 Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.55% | Input $0.030 | Output $0.180 | Precision bf16 | Uptime (1d) 99.54% | | Seller CoreWeave coreweave/fp4 Endpoint terms Cached input /M $0.030 Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.85% | Input $0.030 | Output $0.170 | Precision fp4 | Uptime (1d) 98.88% | | Seller DeepInfra deepinfra/bf16 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.81% | Input $0.037 | Output $0.170 | Precision bf16 | Uptime (1d) 98.74% | | Seller AkashML akashml/bf16 Endpoint terms Cached input /M $0.037 Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.93% | Input $0.037 | Output $0.187 | Precision bf16 | Uptime (1d) 99.95% | | Seller Mancer 2 mancer/fp8 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.90% | Input $0.045 | Output $0.250 | Precision fp8 | Uptime (1d) 97.70% | | Seller Crusoe crusoe/bf16 Endpoint terms Cached input /M $0.050 Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.99% | Input $0.050 | Output $0.250 | Precision bf16 | Uptime (1d) 99.99% | | Seller Novita novita/fp4 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 32,768 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.67% | Input $0.050 | Output $0.250 | Precision fp4 | Uptime (1d) 98.73% | | Seller DigitalOcean digitalocean Endpoint terms Cached input /M $0.012 Context limit 128,000 tokens Output limit 4,096 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.97% | Input $0.060 | Output $0.420 | Precision undeclared | Uptime (1d) 99.98% | | Seller Google google-vertex/global Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 74.27% | Input $0.090 | Output $0.360 | Precision undeclared | Uptime (1d) 66.28% | | Seller BaseTen baseten/fp4 Endpoint terms Cached input /M $0.100 Context limit 128,072 tokens Output limit 115,264 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.98% | Input $0.100 | Output $0.500 | Precision fp4 | Uptime (1d) 99.96% | | Seller BaseTen baseten/fp4 Endpoint terms Cached input /M $0.100 Context limit 128,072 tokens Output limit 115,264 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.100 | Output $0.500 | Precision fp4 | Uptime (1d) 99.99% | | Seller Parasail parasail/fp4 Endpoint terms Cached input /M $0.055 Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.99% | Input $0.100 | Output $0.750 | Precision fp4 | Uptime (1d) 99.97% | | Seller SambaNova sambanova Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.93% | Input $0.140 | Output $0.950 | Precision undeclared | Uptime (1d) 99.81% | | Seller DeepInfra deepinfra/turbo Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.92% | Input $0.150 | Output $0.600 | Precision bf16 | Uptime (1d) 99.98% | | Seller SiliconFlow siliconflow/fp8 Endpoint terms Cached input /M $0.075 Context limit 131,072 tokens Output limit 8,192 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 47.14% | Input $0.150 | Output $0.600 | Precision fp8 | Uptime (1d) 91.35% | | Seller Nebius nebius/fp4 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.84% | Input $0.150 | Output $0.600 | Precision fp4 | Uptime (1d) 97.80% | | Seller Amazon Bedrock amazon-bedrock/eu-west-1 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.150 | Output $0.600 | Precision undeclared | Uptime (1d) 99.97% | | Seller Amazon Bedrock amazon-bedrock Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.150 | Output $0.600 | Precision undeclared | Uptime (1d) 99.41% | | Seller Phala phala Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 32,768 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.60% | Input $0.150 | Output $0.600 | Precision undeclared | Uptime (1d) 99.31% | | Seller Together together Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 67.98% | Input $0.150 | Output $0.600 | Precision undeclared | Uptime (1d) 87.70% | | Seller Groq groq Endpoint terms Cached input /M $0.075 Context limit 131,072 tokens Output limit 65,536 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.78% | Input $0.150 | Output $0.600 | Precision undeclared | Uptime (1d) 99.39% | | Seller Mara mara Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 117,964 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 94.23% | Input $0.150 | Output $0.750 | Precision undeclared | Uptime (1d) 96.50% | | Seller Cerebras cerebras/fp16 Endpoint terms Cached input /M $0.350 Context limit 131,072 tokens Output limit 40,960 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.98% | Input $0.350 | Output $0.750 | Precision fp16 | Uptime (1d) 99.98% | ### Independent scores | LMArena Elo | 1365.4 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. #### Best rankings by task - Game development #110 1005 - Data visualisation #110 995 - 3D #111 909 - UI components #116 932 - Code categories #120 967 - Websites #122 974 Per-task Elo and rank from [Design Arena](https://designarena.ai), via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list. ### Capability | Context window | 131K | | --- | --- | | Max output | 117K | | Input modes | text | | Tool use | yes | | Reasoning | always on | | Knowledge cutoff | 2024-06-30 | | Open weights | yes | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | | Cross-checked | [vendor page](https://openrouter.ai/api/v1/models) | This is the gpt-oss-120b API row. A search that names Claude Sonnet 4.6 as the other side is answered on the compare page, not by blending the two SKUs here. ## Our take editorial — not a measurement The practical reason to consider this model is deployment control: the accepted record identifies open weights and an Apache licence. Review the actual licence and serving requirements before deployment. Hosted offers are seller-specific; self-hosting replaces token charges with hardware, operations and capacity costs rather than eliminating cost. Use the current proof for measured capability and the offer table for hosted prices. ### Strengths - Open weights and a licence identifier are recorded - Text input, tool use and reasoning support are listed ### Weaknesses - A hosted endpoint can impose its own limits - Self-hosted capacity and operating costs need a separate estimate ### Reach for it when - Deployment-control and self-hosting evaluations - Text workloads with explicit capacity planning ### Avoid it if - You require image or audio input - You cannot operate the serving infrastructure you plan to use Sources: [openrouter.ai](https://openrouter.ai/api/v1/models) 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... ## Questions this page answers What does gpt-oss-120b cost? $0.030/M in, $0.170/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does gpt-oss-120b have an independent quality score? gpt-oss-120b has an LMArena score in this catalogue. What beats gpt-oss-120b? Nothing is both better and cheaper than gpt-oss-120b. Does this page use Artificial Analysis scores for gpt-oss-120b? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Is the cheapest gpt-oss-120b endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.030/M from DekaLLM. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options OpenAI: gpt-oss-120b. Balanced workload. Frontier. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Side by side [Claude Sonnet 4.6](/compare/anthropic__claude-sonnet-4.6--vs--openai__gpt-oss-120b/) - Nearby on the capability axis [o1](/models/openai__o1/) - Same vendor [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) - OpenAI models [OpenAI](/providers/openai/) - Where this model appears [frontier](/frontier/) - Side by side [DeepSeek V4 Flash 0423](/compare/deepseek__deepseek-v4-flash--vs--openai__gpt-oss-120b/) - Nearby on the capability axis [Nova 2 Lite](/models/amazon__nova-2-lite-v1/) - Same vendor [GPT-5 Mini](/models/openai__gpt-5-mini/) - Where this model appears [knee](/knee/) - Side by side [Gemma 3 4B](/compare/google__gemma-3-4b-it--vs--openai__gpt-oss-120b/) - Nearby on the capability axis [Qwen3 235B A22B](/models/qwen__qwen3-235b-a22b/) - Same vendor [o4 Mini](/models/openai__o4-mini/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![gpt-oss-120b — Undominated.ai dominance verdict](https://undominated.ai/badge/openai__gpt-oss-120b.svg)](https://undominated.ai/models/openai__gpt-oss-120b/) HTML Copy gpt-oss-120b — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/openai__gpt-oss-120b.svg](https://undominated.ai/badge/openai__gpt-oss-120b.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)