Qwen3-235B-A22B Instruct (2507)

July 2025 update of Qwen3-235B-A22B in instruction mode, a 235B MoE with 22B active, improving math, coding and long-context understanding over the April release.

Params: 235B, 22B active
Context: 262K tokens
Max output: 66K
License: Apache 2.0

Visit Alibaba Cloud Compare vs other LLMs →

Hosted API price

List price via Alibaba Cloud · per 1M tokens

USD

Input: $0.23 /1M
Output: $0.92 /1M
Cheapest: $0.09 / $0.58 via Novita
Hosted by: 5 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Qwen3-235B-A22B Instruct (2507), cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Qwen3-235B-A22B Instruct (2507), with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Novita Cheapest	$0.09	$0.58	$2.06	Visit website
Lyceum	$0.20	$0.60	$3.20	Visit website
Together AI	$0.20	$0.60	$3.20	Visit website
Alibaba Cloud Creator	$0.23	$0.92	$4.14	Visit website
Replicate	$0.264	$1.06	$4.76	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Qwen3-235B-A22B Instruct (2507) needs about 137 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 3090 at about $1,440 a month.

That costs the same as roughly 4B tokens a month on Alibaba Cloud's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Qwen3-235B-A22B Instruct (2507) at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 262K context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	137 GB157 GB	8× RTX 3090	$1,440$2,477	4B tokens /mo7B tokens /mo
8-bit FP8 / INT8	243 GB288 GB	8× RTX A6000	$3,283$3,283	10B tokens /mo10B tokens /mo
16-bit FP16 / BF16	478 GB523 GB	8× A100	$9,850$9,850	29B tokens /mo29B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Similarly priced models

The models nearest Qwen3-235B-A22B Instruct (2507) by blended rate, each at its own cheapest provider.

Models priced nearest Qwen3-235B-A22B Instruct (2507) per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Qwen3-235B-A22B Instruct (2507)
Llama 3.2 11B Vision Meta	$0.1535	$0.049	$0.676	128K	Dec 2023	−11%
Nemotron 3 Super 120B A12B Nvidia	$0.1583	$0.09	$0.50	1M	Jun 2025	−8%
MiMo-V2.6-Flash Xiaomi MiMo	$0.1633	$0.14	$0.28	1M		−5%
GPT-6 Luna OpenAI	$0.1667	$0.10	$0.50	1M	May 2026	−3%
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	−1%
Qwen3-235B-A22B Instruct (2507) This model Alibaba Cloud	$0.1717	$0.09	$0.58	262K
Llama 3.3 70B Meta	$0.175	$0.13	$0.40	128K	Dec 2023	+2%
Qwen3.5-27B Alibaba Cloud	$0.1863	$0.086	$0.688	262K		+9%
Hy3 Tencent	$0.198	$0.132	$0.528	262K		+15%
Ministral 3 14B Mistral	$0.20	$0.20	$0.20	256K		+17%
Qwen3.8-Flash Alibaba Cloud	$0.2033	$0.15	$0.47	1M		+18%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Salad

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Capabilities

What Qwen3-235B-A22B Instruct (2507) accepts and can do, as published by Alibaba Cloud.

Text Accepts and generates natural-language text.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.

Common questions

What is Qwen3-235B-A22B Instruct (2507) good for?

Long-context instruction following without a reasoning trace. Apache 2.0 weights, on a multi-GPU node.

When is Qwen3-235B-A22B Instruct (2507) not a good fit?

Tasks that need a thinking mode: this release is non-thinking only, and the Thinking (2507) sibling covers that. Self-hosting takes a multi-GPU node.

What is the cheapest way to run Qwen3-235B-A22B Instruct (2507)?

Hosted, unless you push serious volume. Alibaba Cloud charges $0.23 in / $0.92 out per 1M tokens. The cheapest rental that fits is 8x RTX 3090 at $1,440 a month, which costs the same as about 4B tokens a month on that API.

Can I self-host Qwen3-235B-A22B Instruct (2507)?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 137 GB of GPU memory, which starts at roughly $1,440 a month on the cheapest rental that fits.