--- title: "Qwen2.5 72B Instruct — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/qwen__qwen-2.5-72b-instruct/ description: "Qwen2.5 72B Instruct: $0.360/M in, $0.400/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # Qwen2.5 72B Instruct — price, capability and what beats it · Undominated.ai > Qwen2.5 72B Instruct: $0.360/M in, $0.400/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/qwen__qwen-2.5-72b-instruct/) [Cheaper alternatives](/alternatives/qwen__qwen-2.5-72b-instruct/) [Family](/families/qwen/) [Compare models](https://undominated.ai/compare/?models=qwen%2Fqwen-2.5-72b-instruct) 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 # Qwen2.5 72B Instruct Qwen · 19 Sept 2024 Balanced Summarise Chat Code gen Agentic BETTER VALUE OPTION ## A stored alternative has an equal-or-higher measured score and an equal-or-lower price. **$0.370** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) · Δ score 200.6 points · 36% lower measured price · $0.238 / 1M tokens [Gemma 3 4B](/models/google__gemma-3-4b-it/) is a further stored option with these losses: no tool use 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 1,269 ± 4.06 · 39,406 votes Context window 32.77K Maximum output 16.38K Input modalities text Output modalities text Published input price $0.360 / 1M tokens Published output price $0.400 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from DeepInfra: 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 | $0.360 /M | | --- | --- | | Output | $0.400 /M | | Cached input | Unknown /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 $0.380/M from Novita. 2 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 DeepInfra deepinfra/fp8 Endpoint terms Cached input /M Unknown Context limit 32,768 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 98.63% | Input $0.360 | Output $0.400 | Precision fp8 | Uptime (1d) 98.80% | | Seller Novita novita/bf16 Endpoint terms Cached input /M Unknown Context limit 32,000 tokens Output limit 8,192 tokens Tools Listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 92.76% | Input $0.380 | Output $0.400 | Precision bf16 | Uptime (1d) 97.40% | ### Independent scores | LMArena Elo | 1269 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. ### Capability | Context window | 32K | | --- | --- | | Max output | 16K | | Input modes | text | | Tool use | yes | | Reasoning | no | | 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 | Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and... ## Questions this page answers What does Qwen2.5 72B Instruct cost? $0.360/M in, $0.400/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Qwen2.5 72B Instruct have an independent quality score? Qwen2.5 72B Instruct has an LMArena score in this catalogue. What beats Qwen2.5 72B Instruct? GLM 5.3 Flash has an equal-or-higher measured score and an equal-or-lower price. Does this page use Artificial Analysis scores for Qwen2.5 72B Instruct? 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 Qwen2.5 72B Instruct endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.380/M from Novita. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Qwen2.5 72B Instruct. Balanced workload. Better value option available. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Both better and cheaper [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) - Higher score and cheaper, with a named trade [Gemma 3 4B](/models/google__gemma-3-4b-it/) - Nearby on the capability axis [GPT-4 Turbo](/models/openai__gpt-4-turbo/) - Same vendor [Qwen2.5 Coder 32B Instruct](/models/qwen__qwen-2.5-coder-32b-instruct/) - Qwen models [Qwen](/providers/qwen/) - Where this model appears [spreads](/spreads/) - Nearby on the capability axis [Mistral Large 2407](/models/mistralai__mistral-large-2407/) - Same vendor [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) - Where this model appears [traps](/traps/) - Nearby on the capability axis [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) - Same vendor [Qwen3 32B](/models/qwen__qwen3-32b/) - Where this model appears [significance](/significance/) ## 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 [![Qwen2.5 72B Instruct — Undominated.ai dominance verdict](https://undominated.ai/badge/qwen__qwen-2.5-72b-instruct.svg)](https://undominated.ai/models/qwen__qwen-2.5-72b-instruct/) HTML Copy Qwen2.5 72B Instruct — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/qwen__qwen-2.5-72b-instruct.svg](https://undominated.ai/badge/qwen__qwen-2.5-72b-instruct.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/)