MODEL PROOF
Qwen3 Next 80B A3B Thinking
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
deal-only price: No offer passes the like-for-like test, so this price is a fallback: precision not disclosed. · precision not disclosed: The seller whose offer sets this price does not declare its serving precision. It is not read as full precision.
DeepSeek V4.1 Flash · Δ score 94.3 points · 56% lower measured price · $0.182 / 1M tokens (Price under confirmation since Oct 12, 2026)
GLM 5.3 Flash is a further stored option with these losses: 236K → 131K max output
- Independent LMArena score
- 1,368.2 ± 5.84 · 13,481 votes
- Context window
- 262.14K
- Maximum output
- 235.93K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.150 / 1M tokens
- Published output price
- $1.20 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Google: no serving offer passes the like-for-like test, so this is a fallback. deal-only price precision not disclosed The seller whose offer sets this price does not declare its serving precision. It is not read as full precision.
Every price dimension · USD per million tokens
| Input | $0.150/M |
|---|---|
| Output | $1.20/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.
1 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) |
|---|---|---|---|---|
| Googlegoogle-vertex/global Endpoint terms
| $0.150 | $1.20 | undeclared | 100.00% |
Independent scores
| LMArena Elo | 1368.2default |
|---|---|
| LMArena row | qwen3-next-80b-a3b-thinking |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Capability
| Context window | 262K |
|---|---|
| Max output | 235K |
| Input modes | text |
| Tool use | yes |
| Reasoning | always on |
| Knowledge cutoff | 2025-09-30 |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-16 |
| Quality data | verified |
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...
Questions this page answers
What does Qwen3 Next 80B A3B Thinking cost?
$0.150/M in, $1.20/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Qwen3 Next 80B A3B Thinking have an independent quality score?
Qwen3 Next 80B A3B Thinking has an LMArena score in this catalogue.
What beats Qwen3 Next 80B A3B Thinking?
DeepSeek V4.1 Flash has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for Qwen3 Next 80B A3B Thinking?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
MODEL MONUMENT
Save or share this proof
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.
[](https://undominated.ai/models/qwen__qwen3-next-80b-a3b-thinking/)<a href="https://undominated.ai/models/qwen__qwen3-next-80b-a3b-thinking/"><img src="https://undominated.ai/badge/qwen__qwen3-next-80b-a3b-thinking.svg" alt="Qwen3 Next 80B A3B Thinking — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/qwen__qwen3-next-80b-a3b-thinking.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.
