Qwen: Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

Qwen3 235B A22B Thinking 2507 is a Qwen model that isn't ranked on the TryAii Score yet — only 2 benchmarks on file so far. It lists at $0.23/$2.3 per million input/output tokens with a 131K-token context. It's reasonably quick at roughly 43-73 tokens/sec.

Prompt $/1M

$0.230

Completion $/1M

$2.300

Context

131,072 tok

Best provider

77 tok/s · Novita

Specs

Model id: qwen/qwen3-235b-a22b-thinking-2507
Display name: Qwen: Qwen3 235B A22B Thinking 2507
Modality: text->text
Tokenizer: Qwen3
Instruct type: qwen3
Context length: 131,072
Max completion: 117,964
Prompt $/1M: $0.230
Completion $/1M: $2.300
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptyes
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Novitafastest	77	977 ms	1,163 ms
Alibaba	73	424 ms	444 ms
WandBfastest	73	397 ms	439 ms
Venice	54	536 ms	603 ms
AtlasCloud	46	1,395 ms	1,956 ms
DeepInfra	41	465 ms	536 ms
SiliconFlow	25	2,626 ms	3,116 ms
qwenfastest	—	—	—