All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

Qwen3.5 35B-A3B

API ID qwen3.5-35b-a3b

qwen3.5-35b-a3b is a Qwen model, released February 2026. It has a 262,144-token context window and up to 65,536 output tokens. It takes image input and supports function calling and structured outputs. Standard price: $0.25 input and $2.00 output per 1M tokens.

Status
Active
Released
February 2026
Shutdown
none announced
Replacement
—

Qwen announces retirement dates without naming the models on a page AIWire can read. AIWire posts each new notice on the wire and will flag qwen3.5-35b-a3b if it disappears from Qwen's model list.

Benchmarks

Scores as each source published them
or

Comparing with Qwen3 30B-A3B Instruct (2507), the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features

Arena

ArenaQwen3.5 35B-A3BQwen3 30B-A3B Instruct (2507)ChangeRankDateSource
Text
By category
  • Math 1398 rank 163 vs 1378 (+20, within range)
  • Creative writing 1342 rank 188 vs 1318 (+24)
  • Instruction following 1386 rank 164 vs 1366 (+20)
  • Hard prompts 1412 rank 175 vs 1407 (+5, within range)
  • Long prompts 1399 rank 173 vs 1381 (+18)
  • Multi-turn 1394 rank 172 vs 1379 (+15, within range)
  • Expert 1420 rank 156 vs 1396 (+24, within range)
1394 ±41382 ±5+12169 of 415
30,480 votes		Oct 13, 2026source
Text: Coding1435 ±71437 ±9−2
within range		175 of 410
8,398 votes		Oct 13, 2026source
WebDev1254 ±17not rated129 of 142
1,617 votes		Oct 13, 2026source

Rated as qwen3.5-35b-a3b; Qwen3 30B-A3B Instruct (2507) as qwen3-30b-a3b-instruct-2507. Ratings come from people voting between two anonymous answers; Text is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

BenchmarkQwen3.5 35B-A3BQwen3 30B-A3B Instruct (2507)ChangeSettingRunSource
GPQA Diamond
Other settings
  • 81.2% vs not run no reasoning
83.5%55.6%+27.9 ptsAug 28, 2026source
OTIS Mock AIME 2024-2025
Other settings
  • 54.4% vs 62.2%
70.0%62.2%+7.8 ptsno reasoning (vs no setting)Aug 30, 2026source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features

Compare models
FeatureValueSinceSource
Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup.Supportedin place when tracking began (October 6, 2026)source
Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result.Supportedin place when tracking began (October 6, 2026)source
Prompt cachingA prompt prefix you send again and again (system prompt, documents, tools) is cached, so later requests cost less and start faster.Not supportedin place when tracking began (October 6, 2026)source
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Not supportedin place when tracking began (October 6, 2026)source
Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read.Supportedin place when tracking began (October 6, 2026)source
Fine-tuningYou can train your own version of the model on your examples through the company's API, then call it like any other model.Not supportedin place when tracking began (October 6, 2026)source
Built-in web searchThe company's API can search the web for the model during a request and cite its sources; you don't need a search service of your own.Supportedin place when tracking began (October 6, 2026)source
Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word.262,144 tokensin place when tracking began (October 6, 2026)source
Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word.65,536 tokensin place when tracking began (October 6, 2026)source

Not published by Qwen: PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

Price history

USD per 1M tokens, standard tier
$0.00$0.50$1.00$1.50$2.00$2.50Oct 2026In $0.25Out $2.00Oct 5, 2026 to Oct 15, 2026: Input $0.25, Output $2.00
$0.00$0.50$1.00$1.50$2.00$2.50Oct 2026In $0.25Out $2.00Oct 5, 2026 to Oct 15, 2026: Input $0.25, Output $2.00

We started recording this model's prices on Oct 5, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 5, 2026Input$0.25
Oct 5, 2026Output$2.00

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$0.25
output$2.00

Changelog

Changes we detected on Qwen's pages

No changes recorded yet.

Email alerts

Get an email if qwen3.5-35b-a3b changes

We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving Qwen's model list.

No password: one email to confirm, and you can unsubscribe any time. Privacy

Last checked · Sources: Qwen models, Qwen deprecations, Qwen free terms