Qwen: Qwen3 Coder Next

qwen/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Prompt $/1M

$0.110

Completion $/1M

$0.800

Context

262,144 tok

Best provider

111 tok/s · AtlasCloud

Specs

Model id: qwen/qwen3-coder-next
Display name: Qwen: Qwen3 Coder Next
Modality: text->text
Tokenizer: Qwen
Instruct type: —
Context length: 262,144
Max completion: 262,144
Prompt $/1M: $0.110
Completion $/1M: $0.800
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
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
AtlasCloud	111	809 ms	938 ms
Artificial Analysis	97	909 ms	—
Ionstreamfastest	87	474 ms	669 ms
Alibaba	72	1,094 ms	1,165 ms
Parasail	62	584 ms	668 ms
Novita	59	1,206 ms	1,516 ms
StreamLake	59	1,093 ms	1,544 ms
Together	31	484 ms	558 ms
Phala	28	1,820 ms	1,900 ms
Chutes	8	4,593 ms	4,765 ms