Alibaba (Qwen)

Qwen3.5 122B-A10B

Type
language model
Context
262K tokens
Max output
66K
Released
23 February 2026
API string
qwen/qwen3.5-122b-a10b
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
EmpirioLabs AI $0.115 $0.917 31 Jul 2026
Merge Gateway $0.115 $0.917 31 Jul 2026
OrcaRouter $0.115 $0.917 31 Jul 2026
libertai $0.25 $1.75 31 Jul 2026
Kilo Code $0.26 $2.08 31 Jul 2026
OpenRouter qwen/qwen3.5-122b-a10b $0.26 $2.08 31 Jul 2026
SiliconFlow $0.26 $2.08 31 Jul 2026
siliconflow-cn $0.29 $2.32 31 Jul 2026
DeepInfra $0.29 $2.4 31 Jul 2026
NanoGPT qwen3.5-122b-a10b $0.36 $2.88 31 Jul 2026
mixlayer $0.4 $3.2 31 Jul 2026
novita-ai $0.4 $3.2 31 Jul 2026
Alibaba (Qwen) $0.4 $3.2 31 Jul 2026
Hugging Face $0.4 $3.2 31 Jul 2026
NEAR AI $0.4 $3.2 31 Jul 2026
OpenRouter openrouter/qwen/qwen3.5-122b-a10b $0.4 $2 31 Jul 2026
Cortecs $0.444 $3.106 31 Jul 2026
NanoGPT TEE/qwen3.5-122b-a10b $0.46 $3.68 31 Jul 2026
tensorx $0.5 $3.5 2 Aug 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

A single provider appears several times if it sells this model under different identifiers and at different prices — for example, at different weight precision. The identifier is shown next to the name. Identical offers that arrived from two sources under different spellings are merged into one row.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in French 1,442.71 1,421–1,464
Arena Score, programming 1,436.07 1,429–1,443
Arena Score, expert questions 1,434.47 1,422–1,447
Arena Score in English 1,428.63 1,423–1,434
Arena Score, mathematics 1,428.55 1,415–1,443
Arena Score, hard prompts 1,421.7 1,416–1,427
Arena Score in Spanish 1,418.53 1,398–1,439
Arena Score, overall 1,417.72 1,413–1,422
Arena Score, multi-turn dialogue 1,414.82 1,406–1,424
Arena Score, long queries 1,410.68 1,404–1,417
Arena Score, instruction following 1,400.29 1,394–1,407
Arena Score in Russian 1,397 1,386–1,408
Arena Score, creative writing 1,369.14 1,360–1,379
Arena Score, web development 1,359.5 1,352–1,367
Arena Score, text recognition in images 1,251.96 1,245–1,259
Arena Score, understanding diagrams 1,251.49 1,240–1,263
Arena Score, working with images 1,246.04 1,239–1,253