MODEL PROOF

Qwen3 30B A3B

BETTER VALUE OPTION

A stored alternative has an equal-or-higher measured score and an equal-or-lower price.

$0.215 / 1M tokens Balanced · 3 tokens in per 1 out

GLM 5.3 Flash · Δ score 154.6 points · 31% lower measured price · $0.148 / 1M tokens

Qwen3 235B A22B Instruct 2507 is a further stored option with these losses: no extended reasoning

Independent LMArena score
1,316.8 ± 4.72 · 26,130 votes
Context window
40.96K
Maximum output
16.38K
Input modalities
text
Output modalities
text
Published input price
$0.120 / 1M tokens
Published output price
$0.500 / 1M tokens
Pricing kind
fixed

Inspect complete billing conditions and endpoint terms below.

Price from DeepInfra: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known.

Cheaper right now: $0.172/M at DeepInfra — delivery tier (flex) It does not pass the like-for-like test, so it never sets a rank.

Every price dimension · USD per million tokens
Input$0.120/M
Output$0.500/M
Cached inputUnknown/M
Cache writeUnknown/M
Cache write 1hUnknown/M
ReasoningUnknown/M

Who sells it

The same weights, different shops. Cheapest is not like-for-like when serving precision differs.

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.

SellerInputOutputPrecisionUptime (1d)
DeepInfradeepinfra/fp8/flex
Endpoint terms
Cached input /M
Unknown
Context limit
40,960 tokens
Output limit
36,864 tokens
Tools
Not listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$0.096 $0.400 fp8 —
DeepInfradeepinfra/fp8
Endpoint terms
Cached input /M
Unknown
Context limit
40,960 tokens
Output limit
16,384 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.120 $0.500 fp8 100.00%
DeepInfradeepinfra/fp8/priority
Endpoint terms
Cached input /M
Unknown
Context limit
40,960 tokens
Output limit
36,864 tokens
Tools
Not listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$0.180 $0.750 fp8 99.16%

Independent scores

LMArena Elo1316.8default
LMArena rowqwen3-30b-a3b

LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.

Best rankings by task

  • Data visualisation #126 967
  • UI components #135 929
  • Code categories #143 923
  • Game development #144 871
  • Websites #145 942

Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.

Capability

Context window40K
Max output16K
Input modestext
Tool useyes
Reasoningoptional
Knowledge cutoff2025-03-31
Open weightsUnknown

Provenance

Price sourceopenrouter.ai
Fetched2026-11-22
Quality dataverified

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Questions this page answers

What does Qwen3 30B A3B cost?

$0.120/M in, $0.500/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.

Does Qwen3 30B A3B have an independent quality score?

Qwen3 30B A3B has an LMArena score in this catalogue.

What beats Qwen3 30B A3B?

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 Qwen3 30B A3B?

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.

Qwen3 30B A3B — Undominated.ai dominance verdict

Markdown
[![Qwen3 30B A3B — Undominated.ai dominance verdict](https://undominated.ai/badge/qwen__qwen3-30b-a3b.svg)](https://undominated.ai/models/qwen__qwen3-30b-a3b/)
HTML
<a href="https://undominated.ai/models/qwen__qwen3-30b-a3b/"><img src="https://undominated.ai/badge/qwen__qwen3-30b-a3b.svg" alt="Qwen3 30B A3B — Undominated.ai dominance verdict" height="36"></a>

Direct file: https://undominated.ai/badge/qwen__qwen3-30b-a3b.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.

Evidence & Ask