--- title: "Qwen: Qwen3 235B A22B Thinking 2507 — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/qwen__qwen3-235b-a22b-thinking-2507/ description: "Qwen: Qwen3 235B A22B Thinking 2507: $0.230/M in, $2.30/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # Qwen: Qwen3 235B A22B Thinking 2507 — price, capability and what beats it · Undominated.ai > Qwen: Qwen3 235B A22B Thinking 2507: $0.230/M in, $2.30/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/qwen__qwen3-235b-a22b-thinking-2507/) [Cheaper alternatives](/alternatives/qwen__qwen3-235b-a22b-thinking-2507/) [Family](/families/qwen/) [Compare models](https://undominated.ai/compare/?models=qwen%2Fqwen3-235b-a22b-thinking-2507) 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 # Qwen3 235B A22B Thinking 2507 Qwen · 25 Jul 2025 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. **$0.748** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) · Δ score 75.8 points · 28% lower measured price · $0.540 / 1M tokens [Gemma 4 31B](/models/google__gemma-4-31b-it/) is a further stored option with these losses: 118K → 16K max output Lifecycle: retirement date · 09 Oct 2026 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 1,415.2 ± 6.55 · 8,774 votes Context window 131.07K Maximum output 117.96K Input modalities text Output modalities text Published input price $0.230 / 1M tokens Published output price $2.30 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from Alibaba: 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 | $0.230 /M | | --- | --- | | Output | $2.30 /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 $0.300/M from Novita. 3 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 Alibaba alibaba 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 $0.230 | Output $2.30 | Precision undeclared | Uptime (1d) 99.74% | | Seller Novita novita/fp8 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 100.00% | Input $0.300 | Output $3.00 | Precision fp8 | Uptime (1d) 99.72% | | Seller Venice venice/fp8 Endpoint terms Cached input /M Unknown Context limit 128,000 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.450 | Output $3.50 | Precision fp8 | Uptime (1d) 99.94% | ### Independent scores | LMArena Elo | 1415.2 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. #### Best rankings by task - 3D #102 1005 - Websites #107 1059 - Code categories #107 1037 - Data visualisation #113 957 - UI components #113 952 - Game development #116 970 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 | 2025-06-30 | | Open weights | Unknown | **Retirement scheduled for 2026-10-09.** Do not start new work on it. ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144... ## Questions this page answers What does Qwen3 235B A22B Thinking 2507 cost? $0.230/M in, $2.30/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Qwen3 235B A22B Thinking 2507 have an independent quality score? Qwen3 235B A22B Thinking 2507 has an LMArena score in this catalogue. What beats Qwen3 235B A22B Thinking 2507? MiMo-V2.6-Pro has an equal-or-higher measured score and an equal-or-lower price. Does this page use Artificial Analysis scores for Qwen3 235B A22B Thinking 2507? 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 Qwen3 235B A22B Thinking 2507 endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.300/M from Novita. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Qwen: Qwen3 235B A22B Thinking 2507. 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 [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) - Higher score and cheaper, with a named trade [Gemma 4 31B](/models/google__gemma-4-31b-it/) - Side by side [Qwen3 235B A22B Instruct 2507](/compare/qwen__qwen3-235b-a22b-2507--vs--qwen__qwen3-235b-a22b-thinking-2507/) - Nearby on the capability axis [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) - Same vendor [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) - Qwen models [Qwen](/providers/qwen/) - Where this model appears [deprecations](/deprecations/) - Nearby on the capability axis [Inkling Small](/models/thinkingmachines__inkling-small/) - Same vendor [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) - Where this model appears [effort](/effort/) - Nearby on the capability axis [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) - Same vendor [Qwen3 Max](/models/qwen__qwen3-max/) ## 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 [![Qwen3 235B A22B Thinking 2507 — Undominated.ai dominance verdict](https://undominated.ai/badge/qwen__qwen3-235b-a22b-thinking-2507.svg)](https://undominated.ai/models/qwen__qwen3-235b-a22b-thinking-2507/) HTML Copy Qwen3 235B A22B Thinking 2507 — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/qwen__qwen3-235b-a22b-thinking-2507.svg](https://undominated.ai/badge/qwen__qwen3-235b-a22b-thinking-2507.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/)