Model

Qwen3 235B-A22B Instruct 2507

Name: Qwen3 235B-A22B Instruct 2507
Brand: alibaba

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

26 providers · 28 listingsreleased Jul 21, 2025open weights

$0.069

lowest input /M · Cortecs

$0.3

lowest output /M · submodel

262K

context window

262K

max output

Compare providers (sorted by listed input price)

24 of 26 providers publish a price for Qwen3 235B-A22B Instruct 2507. The cheapest full-context option is OpenRouter at $0.087/$0.35 per M. Listed prices span 10.8× for identical weights.

			Cache read /M	Cache write /M		Capabilities
Cortecs qwen3-235b-a22b-instruct-2507	$0.069	$0.455	$0.018	—	262K	no reasoningtoolsstructuredno vision	Jul 21, 2025
OpenRouter qwen/qwen3-235b-a22b-2507	$0.087	$0.35	$0.018	—	262K	no reasoningtoolsstructuredno vision	Jul 21, 2025
LLM Gatewayvariant novita/qwen3-235b-a22b-instruct-2507	$0.09	$0.58	—	—	131K	no reasoningtoolsno structuredno vision	Jul 21, 2025
NovitaAI qwen/qwen3-235b-a22b-instruct-2507	$0.09	$0.58	—	—	131K	no reasoningtoolsstructuredno vision	Jul 22, 2025
DevPass (LLM Gateway) qwen3-235b-a22b-instruct-2507	$0.09	$0.58	—	—	262K	no reasoningtoolsstructuredno vision	Jul 8, 2025
Deep Infra Qwen/Qwen3-235B-A22B-Instruct-2507	$0.09	$0.55	—	—	262K	no reasoningtoolsstructuredno vision	Jul 21, 2025
Meganova Qwen/Qwen3-235B-A22B-Instruct-2507	$0.09	$0.6	—	—	262K	no reasoningtoolsstructuredno vision	Jul 23, 2025
Merge Gateway qwen/qwen3-235b-a22b-instruct-2507	$0.1	$0.6	$0.05	—	131K	no reasoningtoolsno structuredno vision	Jul 21, 2025
NanoGPT qwen/Qwen3-235B-A22B-Instruct-2507	$0.13	$0.5	$0.065	—	262K	no reasoningtoolsstructuredno vision	Jul 21, 2025
Abacus Qwen/Qwen3-235B-A22B-Instruct-2507	$0.13	$0.6	—	—	262K	reasoningtoolsno structuredno vision	Jul 1, 2025
Kilo Gateway qwen/qwen3-235b-a22b-2507	$0.149	$0.598	—	—	262K	no reasoningtoolsstructuredno vision	Jul 21, 2025
Jiekou.AI qwen/qwen3-235b-a22b-instruct-2507	$0.15	$0.8	—	—	131K	no reasoningtoolsstructuredno vision	Jan 1, 2026
Venice AI qwen3-235b-a22b-instruct-2507	$0.15	$0.75	—	—	128K	no reasoningtoolsstructuredno vision	Jun 11, 2026
Nebius Token Factory Qwen/Qwen3-235B-A22B-Instruct-2507	$0.2	$0.6	—	—	262K	no reasoningtoolsno structuredno vision	Oct 4, 2025
submodel Qwen/Qwen3-235B-A22B-Instruct-2507	$0.2	$0.3	—	—	262K	no reasoningtoolsno structuredno vision	Aug 23, 2025
LLM Gatewayvariant vertex-openai/qwen3-235b-a22b-instruct-2507	$0.22	$0.88	—	—	262K	no reasoningtoolsno structuredno vision	Jul 21, 2025
Vercel AI Gateway alibaba/qwen-3-235b	$0.22	$0.88	—	—	262K	reasoningtoolsno structuredno vision	Apr 1, 2025
Crusoe Qwen/Qwen3-235B-A22B-Instruct-2507	$0.22	$0.8	$0.11	—	262K	no reasoningtoolsno structuredno vision	Jul 21, 2025
Amazon Bedrock qwen.qwen3-235b-a22b-2507-v1:0	$0.22	$0.88	—	—	262K	no reasoningtoolsstructuredno vision	Sep 18, 2025
Eden AI qwen/qwen3-235b-a22b-instruct-2507	$0.23	$0.92	—	—	131K	no reasoningno toolsstructuredno vision	Jul 21, 2025

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.087▲ 26.8%
Best output /M: $0.35▼ 23.1%
Provider coverage: 28; 27 at the start · 24 snapshots

Best input priceBest output priceAug 21, 2026 → Sep 14, 2026

Price badge

![Qwen3 235B-A22B Instruct 2507 price](https://www.vaanalytics.in/badge/alibaba/qwen3-235b-a22b-instruct-2507.svg)

https://www.vaanalytics.in/badge/alibaba/qwen3-235b-a22b-instruct-2507.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →

capabilityvia amazon-bedrock · Sep 13, 2026
- name: Qwen3 235B A22B 2507 → Qwen3 235B-A22B Instruct 2507
- description: Qwen instruction model for multilingual chat, reasoning, and tool use → Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use
- knowledge: 2024-04 → —
- release_date: 2025-09-18 → 2025-07-21
contextvia kilo · Sep 13, 2026
- output: 16K → 236K tokens
repricedvia openrouter · Sep 13, 2026
- output: 16K → 236K tokens
- input: $0.22 → $0.087
- output: $0.88 → $0.35
- cache_read: — → $0.018
repricedvia openrouter · Sep 10, 2026
- input: $0.09 → $0.22
- output: $0.55 → $0.88
contextvia kilo · Sep 5, 2026
- output: 236K → 16K tokens
new modelvia crusoe · Sep 5, 2026

Weights

Permissiveapache-2.0235B params

Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.

licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary

Hugging Face

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.