--- title: "OpenAI: gpt-oss-20b — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/openai__gpt-oss-20b/ description: "OpenAI: gpt-oss-20b: $0.018/M in, $0.090/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # OpenAI: gpt-oss-20b — price, capability and what beats it · Undominated.ai > OpenAI: gpt-oss-20b: $0.018/M in, $0.090/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/openai__gpt-oss-20b/) [Cheaper alternatives](/alternatives/) [Family](/families/gpt-oss/) [Compare models](https://undominated.ai/compare/?models=openai%2Fgpt-oss-20b) 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-20b OpenAI · 05 Aug 2025 Balanced Summarise Chat Code gen Agentic FRONTIER ## Nothing is both better and cheaper under this workload. **$0.036** / 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) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,287.7 ± 6.4 · 10,368 votes Context window 131.07K Maximum output 32.77K Input modalities text Output modalities text Published input price $0.018 / 1M tokens Published output price $0.090 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from Darkbloom: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known. Every price dimension · USD per million tokens | Input | $0.018 /M | | --- | --- | | Output | $0.090 /M | | Cached input | $0.0090 /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 $0.029/M from DekaLLM. 12 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 Darkbloom darkbloom/fp8 Endpoint terms Cached input /M $0.0090 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 99.95% | Input $0.018 | Output $0.090 | Precision fp8 | Uptime (1d) 99.72% | | Seller AkashML akashml/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 99.22% | Input $0.020 | Output $0.100 | Precision fp4 | Uptime (1d) 99.19% | | Seller DekaLLM dekallm/bf16 Endpoint terms Cached input /M $0.029 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 99.92% | Input $0.029 | Output $0.140 | Precision bf16 | Uptime (1d) 99.45% | | 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 100.00% | Input $0.030 | Output $0.140 | Precision bf16 | Uptime (1d) 99.92% | | 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 100.00% | Input $0.030 | Output $0.130 | Precision fp4 | Uptime (1d) 99.94% | | Seller Parasail parasail/fp4 Endpoint terms Cached input /M $0.020 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 99.96% | Input $0.030 | Output $0.150 | Precision fp4 | Uptime (1d) 99.92% | | Seller SiliconFlow siliconflow/fp8 Endpoint terms Cached input /M Unknown 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 94.09% | Input $0.040 | Output $0.180 | Precision fp8 | Uptime (1d) 84.84% | | Seller Novita novita/fp4 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 32,768 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.040 | Output $0.150 | Precision fp4 | Uptime (1d) 99.96% | | 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 Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes Unknown | Input $0.070 | Output $0.150 | Precision undeclared | Uptime (1d) 99.94% | | Seller Amazon Bedrock amazon-bedrock 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 99.99% | Input $0.070 | Output $0.150 | Precision undeclared | Uptime (1d) 99.95% | | Seller Google google-vertex/us-central1 Endpoint terms Cached input /M Unknown Context limit 131,072 tokens Output limit 32,768 tokens Tools Not listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 96.79% | Input $0.070 | Output $0.250 | Precision undeclared | Uptime (1d) 96.42% | | Seller Groq groq Endpoint terms Cached input /M $0.038 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 97.94% | Input $0.075 | Output $0.300 | Precision undeclared | Uptime (1d) 97.91% | ### Independent scores | LMArena Elo | 1287.7 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. #### Best rankings by task - Data visualisation #115 940 - Websites #129 859 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 | 32K | | Input modes | text | | Tool use | yes | | Reasoning | always on | | Knowledge cutoff | 2024-06-30 | | Open weights | Unknown | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for... ## Questions this page answers What does gpt-oss-20b cost? $0.018/M in, $0.090/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does gpt-oss-20b have an independent quality score? gpt-oss-20b has an LMArena score in this catalogue. What beats gpt-oss-20b? Nothing is both better and cheaper than gpt-oss-20b. Does this page use Artificial Analysis scores for gpt-oss-20b? 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-20b endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.029/M from DekaLLM. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options OpenAI: gpt-oss-20b. 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 [Gemma 3 4B](/compare/google__gemma-3-4b-it--vs--openai__gpt-oss-20b/) - Nearby on the capability axis [Gemma 3 4B](/models/google__gemma-3-4b-it/) - Same vendor [GPT-4o (2024-08-06)](/models/openai__gpt-4o-2024-08-06/) - OpenAI models [OpenAI](/providers/openai/) - Where this model appears [frontier](/frontier/) - Side by side [Llama 3.1 8B Instruct](/compare/meta-llama__llama-3.1-8b-instruct--vs--openai__gpt-oss-20b/) - Nearby on the capability axis [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) - Same vendor [GPT-4o (2024-05-13)](/models/openai__gpt-4o-2024-05-13/) - Where this model appears [knee](/knee/) - Nearby on the capability axis [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) - Same vendor [GPT-4 Turbo](/models/openai__gpt-4-turbo/) - Where this model appears [wire](/wire/) ## 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-20b — Undominated.ai dominance verdict](https://undominated.ai/badge/openai__gpt-oss-20b.svg)](https://undominated.ai/models/openai__gpt-oss-20b/) HTML Copy gpt-oss-20b — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/openai__gpt-oss-20b.svg](https://undominated.ai/badge/openai__gpt-oss-20b.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/)