Inference
EN
Alibaba

Qwen3.5 9B

Qwen3.5 9B is a model from Alibaba. It has 3 scored results in 3 categories. It has no index.

  • Open weights
  • Input: text · image · video
  • Released 2026-03
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.30%
SpeedOutput tokens per second.126/sMedian 67/s
First tokenSeconds to the first output token.0.2 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.126Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.186Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
qwen/qwen3.5-9b
Max outputMaximum output tokens per request.
41K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.114
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
6 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterDeprecatedRouter$0.056$0.083262K
Deep InfraHost$0.10$0.15262K
SiliconFlowHost$0.10$0.15262K
OVHcloudCloud$0.12$0.18262K
Together AIHost$0.17$0.25262K
RegoloHost$0.079$0.393262K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.1 counted49.6—
MultilingualTasks in many languages.1 counted45.0—
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted44.8—

Results

3 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
EuroEval ItalianMultilingual56.9% ±0.640 / 174
EuroEval SwedishMultilingual54.6% ±0.952 / 195
EuroEval GermanMultilingual46.7% ±0.752 / 191
EuroEval PolishMultilingual52.7% ±0.557 / 209
EuroEval PortugueseMultilingual55.0% ±0.652 / 182
EuroEval SpanishMultilingual46.1% ±0.757 / 176
EuroEval FrenchMultilingual55.5% ±0.660 / 178
EuroEval DutchMultilingual52.2% ±0.560 / 175
GPQA diamond · Epoch AIKnowledge78.9% ±2.492 / 217
OTIS Mock AIME 2024-2025Math61.7% ±6.0110 / 200

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYEuroEvalMITmodels.devMIT

History

5 releases
Output / 1M$0.15 → $0.186
23 Oct 202612 Nov 2026

Questions

How much does Qwen3.5 9B cost?
$0.126 per 1M input tokens, $0.186 per 1M output tokens.
How fast is Qwen3.5 9B?
126 output tokens per second, 0.2 s to the first token.
What is the context window of Qwen3.5 9B?
262K tokens.
Is Qwen3.5 9B open source?
Yes. Its weights are published.
When was Qwen3.5 9B released?
March 2026.

More from Alibaba

All models
Qwen3.5-122B-A10B51.9Qwen3.5-27B51.3Qwen3.5-35B-A3B49.4Qwen3.5 FlashUnrankedQwen3.5 PlusUnranked