Skip to main content
Back to Explore

Qwen3.5 122B A10B (Non-reasoning)

Alibaba·Released 2026-02-24
Open Source

Pricing

Input

$0.40

per 1M tokens

Output

$3.20

per 1M tokens

Blended

$1.10

per 1M tokens

Cheaper than 35% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$1.10

Monthly

$33.00

vs. Similar Models

Claude 4.1 Opus (Non-reasoning)Q:+0.1
$30.00+2627%
MiniMax: MiniMax M2Q:+0.2
$0.44-60%
MiMo-V2.5-Pro (Non-reasoning)Q:-0.2
$1.35+23%
GPT-5.4 (Non-reasoning)Q:-0.4
$5.91+437%

Performance

177

tokens/sec

Faster than 83% of models

1.17

seconds

Faster than 45% of models

1.17

seconds

Faster than 63% of models

Market Median

94 tok/s

89% faster

Median TTFT

1.10s

5% slower

Throughput/Dollar

161

tok/s per $/1M

Speed Comparison

OpenAI: GPT-5.4 Mini
177 tok/s+0%
OpenAI: GPT-5 Codex
177 tok/s-0%
Nova 2.0 Lite (high)
178 tok/s+0%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
82.7%
HLE
14.8%
LiveCodeBenchNot evaluated
SciCode
35.6%
TerminalBench Hard
29.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
50.8%
Long Context Recall
56.0%
Tau2
84.5%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models