ZappushZappush
SkillsUse CasesBenchmarkCommunity
← Qwen Models

Qwen

Qwen3 Next 80b A3b Thinking

qwen/qwen3-next-80b-a3b-thinking

131.1K context·32.8K max output·text->text

Input

$0.0975

per 1M tokens

Output

$0.7800

per 1M tokens

Cache Read

-

not available

Cache Write

-

not available

Quality Benchmarks

StrongValue: -4611

Coding

Code generation, completion, debugging

29.3

Math

Competition math, calculus, olympiad

74.3

Reasoning

Logic, spatial, puzzle solving

54.2

Language

Summarization, paraphrase, writing

45.1

Overall

50.7

Source: LiveBench (livebench.ai) / Scores 0-100

Capabilities

VisionTool UseReasoningPrompt Caching

Similar Price Range

Nemotron 3 Super 120b A12b

NVIDIA

$0.1000 in$0.5000 out262.1K

Step 3.5 Flash

Stepfun

$0.1000 in$0.3000 out256K

Llama 3.3 Nemotron Super 49b V1.5

NVIDIA

$0.1000 in$0.4000 out131.1K

More from Qwen

Qwen2.5 Coder 7b Instruct

$0.0300 / $0.0900

Qwen Turbo

$0.0325 / $0.1300

Qwen 2.5 7b Instruct

$0.0400 / $0.1000

Qwen3.5 9b

$0.0500 / $0.1500

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.

Deploy Your Agent
Zappush© 2026 Zappush
HomeSkillsUse CasesBenchmarkGuarantee