---
title: "Qwen3 32B FP8 API pricing: 5 providers compared | BroadRouter"
description: "Qwen3 32B FP8 API price per token from 5 providers: lowest listed USD 0.08 input and USD 0.28 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/qwen3-32b/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Qwen3 32B FP8 API pricing

Updated 2026-11-15

Among the 5 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Qwen3 32B FP8 is DeepInfra at USD 0.08 per 1M input tokens and USD 0.28 per 1M output tokens. The median across 5 standard prices is USD 0.102 / USD 0.57. Each price is read from the provider's own pricing page.

Qwen · slug `qwen3-32b` · up to 131,072 tokens of context · 5 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-15. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/). Archived list prices since 2025-07-09 (17 archived price points, 2 list-price changes): [LLM API price history](https://broadrouter.com/data/llm-api-price-history/#p-deepinfra).

## Does Qwen sell Qwen3 32B FP8 directly?

Qwen publishes no price for Qwen3 32B FP8 on its own API that we could find, so this page compares hosts only.

## Qwen3 32B FP8 model facts

Facts from Qwen's model card for [`Qwen/Qwen3-32B`](https://huggingface.co/Qwen/Qwen3-32B) and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Qwen3 32B FP8: facts as stated by the model card and the Hugging Face model API, with sources
| Fact | As stated | Source |
| --- | --- | --- |
| Open weights | Yes. The weights are in a public Hugging Face repository (Qwen/Qwen3-32B) with no access gate. | [Hugging Face model API](https://huggingface.co/api/models/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “"private": false, "gated": false, 17 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | [Qwen model card metadata](https://huggingface.co/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “license: apache-2.0” |
| Total parameters | 32.8B | [Qwen model card](https://huggingface.co/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “Number of Parameters: 32.8B” |
| Context length | 32,768 tokens natively; 131,072 tokens with YaRN | [Qwen model card](https://huggingface.co/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “Context Length: 32,768 natively and 131,072 tokens with YaRN.” |
| Input and output | Text in, text out (the card's task tag is text-generation) | [Qwen model card metadata](https://huggingface.co/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “pipeline_tag: text-generation” |
| Tool calling | Yes | [Qwen model card](https://huggingface.co/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “Qwen3 excels in tool calling capabilities.” |
| First published on Hugging Face (not necessarily the release date) | 2025-04-27 | [Hugging Face model API](https://huggingface.co/api/models/Qwen/Qwen3-32B), checked 2026-11-16 · Quote: “"createdAt": "2025-04-27T03:52:59.000Z"” |

## Qwen3 32B FP8 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.0× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Qwen3 32B FP8 API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** cheapest · `Qwen/Qwen3-32B` · Quote: “$0.08 in $0.28 out / 1M tokens” | USD 0.08 | not published | USD 0.28 | USD 0.13 | 40,960 | FP8 | [DeepInfra page](https://deepinfra.com/Qwen/Qwen3-32B) · checked 2026-11-14 · re-checked 2026-11-16 |
| 2 | **[Featherless](https://broadrouter.com/llm-api-pricing/providers/featherless/)** · `Qwen/Qwen3-32B` · Note: Developer plan (per-token billing, from 50 USD a month in credits). Quote: “PRICING: INPUT $0.102 / CACHED $0.0816 / OUTPUT $0.493” | USD 0.102 | USD 0.0816 | USD 0.493 | USD 0.1997 | 32,768 | FP8 | [Featherless page](https://featherless.ai/models/Qwen/Qwen3-32B) · checked 2026-11-15 · re-checked 2026-11-16 |
| 3 | **[GMI Cloud](https://broadrouter.com/llm-api-pricing/providers/gmi-cloud/)** · `Qwen/Qwen3-32B-FP8` · Note: No cache-read price published. Quote: “Price (per 1M tokens) Input $0.10 Output $0.60” | USD 0.10 | not published | USD 0.60 | USD 0.225 | 32,768 | FP8 | [GMI Cloud page](https://console.gmicloud.ai/model/llm/qwen3-32b-fp8/ae9cad4b-9b87-4b80-99e2-4a73f5715a87) · checked 2026-11-15 · re-checked 2026-11-16 |
| 4 | **[SiliconFlow](https://broadrouter.com/llm-api-pricing/providers/siliconflow/)** · Note: Context shown as 131K. Quote: “Qwen3-32B 131K $0.14 $0.57” | USD 0.14 | not published | USD 0.57 | USD 0.2475 | 131,072 | not stated | [SiliconFlow page](https://www.siliconflow.com/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 5 | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** · Note: Standard tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1). Quote: “Qwen3 32B $0.15 $0.60” | USD 0.15 | not published | USD 0.60 | USD 0.2625 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** batch · Note: Batch tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1). Quote: “Qwen3 32B $0.075 $0.30” | USD 0.075 | not published | USD 0.30 | USD 0.1312 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** flex / spot · `Qwen/Qwen3-32B` · Note: Flex service tier (0.8× standard). Quote: “Flex (0.8×) $0.064 $0.224” | USD 0.064 | not published | USD 0.224 | USD 0.104 | 40,960 | FP8 | [DeepInfra page](https://deepinfra.com/Qwen/Qwen3-32B) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** flex / spot · Note: Flex tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1). Quote: “Qwen3 32B $0.075 $0.30” | USD 0.075 | not published | USD 0.30 | USD 0.1312 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** priority · `Qwen/Qwen3-32B` · Note: Priority service tier (1.5× standard). Quote: “Priority (1.5×) $0.12 $0.42” | USD 0.12 | not published | USD 0.42 | USD 0.195 | 40,960 | FP8 | [DeepInfra page](https://deepinfra.com/Qwen/Qwen3-32B) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** priority · Note: Priority tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1). Quote: “Qwen3 32B $0.2625 $1.05” | USD 0.2625 | not published | USD 1.05 | USD 0.4594 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Other tiers (batch, flex / spot and priority):** batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Qwen3%2032B%20FP8%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fqwen3-32b%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does Qwen3 32B FP8 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=qwen3-32b). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on Qwen3 32B FP8, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **DeepInfra** | USD 12.24 | USD 23.40 | exceeds context |
| **Featherless** | USD 16.95 | USD 30.41 | exceeds context |
| **GMI Cloud** | USD 19.80 | USD 33.00 | exceeds context |
| **SiliconFlow** | USD 22.86 | USD 42.15 | USD 303.30 |
| **Amazon Bedrock** | USD 24.30 | USD 45.00 | USD 324.00 |

For the support chatbot, the cheapest price (DeepInfra, USD 12.24 a month) saves USD 7.56 against the median (USD 19.80). For the coding agent the gap is USD 64.80 a month (28% lower).

## Which Qwen3 32B FP8 provider is cheapest for your traffic?

DeepInfra has the lowest input price (USD 0.08) and the lowest output price (USD 0.28), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

Qwen3 32B FP8: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **DeepInfra** (no cache price) | USD 0.13 cheapest | USD 0.13 cheapest | USD 0.13 cheapest |
| **Featherless** | USD 0.1997 | USD 0.1921 | USD 0.186 |
| **GMI Cloud** (no cache price) | USD 0.225 | USD 0.225 | USD 0.225 |
| **SiliconFlow** (no cache price) | USD 0.2475 | USD 0.2475 | USD 0.2475 |
| **Amazon Bedrock** (no cache price) | USD 0.2625 | USD 0.2625 | USD 0.2625 |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

1 of 5 providers publishes a cached-input price below the input price: Featherless (20% off). DeepInfra, GMI Cloud, SiliconFlow and Amazon Bedrock publish none, so cached tokens there bill at the input price.

Context windows differ: 131,072 tokens at SiliconFlow; 40,960 tokens at DeepInfra; 32,768 tokens at Featherless and GMI Cloud. Amazon Bedrock does not state one. The cheapest row is not always the one that fits a long prompt.

## What does Qwen3 32B FP8 cost in other languages?

The same text needs a different number of tokens in each language. With the Qwen3 32B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Qwen3 32B FP8:

| Content | Input per 1M characters | Cheapest provider |
| --- | --- | --- |
| English | USD 0.018 | DeepInfra |
| Arabic MSA | USD 0.031 | DeepInfra |
| Hindi | USD 0.074 | DeepInfra |
| Chinese | USD 0.051 | DeepInfra |
| Code | USD 0.021 | DeepInfra |

From BroadRouter's [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/), which covers 15 languages and content types for every model we could match to a measured tokenizer.

## Estimate your own bill

-   [LLM API cost calculator with Qwen3 32B FP8 preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=qwen3-32b): your traffic and cache rate, against any of 431 models.
-   [Qwen3 token counter](https://broadrouter.com/tools/qwen3-token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

## How does Qwen3 32B FP8 compare with other Qwen models?

The Qwen models whose cheapest standard price is closest to Qwen3 32B FP8's (USD 0.13 blended):

Qwen models priced closest to Qwen3 32B FP8
| Model | Cheapest input | Cheapest output | Max context | Providers |
| --- | --- | --- | --- | --- |
| [Qwen3 Coder 30B A3B](https://broadrouter.com/llm-api-pricing/qwen3-coder-30b-a3b-instruct/) | USD 0.07 | USD 0.28 | 262,144 | 3 |
| [Qwen3-14B](https://broadrouter.com/llm-api-pricing/qwen3-14b/) | USD 0.07 | USD 0.28 | 131,072 | 3 |
| [Qwen3 30B A3B (fp8)](https://broadrouter.com/llm-api-pricing/qwen3-30b-a3b/) | USD 0.051 | USD 0.335 | 40,960 | 3 |
| [Qwen3-30B-A3B-Instruct-2507](https://broadrouter.com/llm-api-pricing/qwen3-30b-a3b-instruct-2507/) | USD 0.09 | USD 0.30 | 262,144 | 2 |
| [Qwen3.5 9B](https://broadrouter.com/llm-api-pricing/qwen3.5-9b/) | USD 0.10 | USD 0.15 | 262,144 | 4 |
| [Qwen3 235B A22B Instruct 2507 FP8](https://broadrouter.com/llm-api-pricing/qwen3-235b-a22b-2507/) | USD 0.0875 | USD 0.35 | 262,144 | 5 |

Priced closest from other makers: [DeepSeek R1 Distill Qwen 7B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-qwen-7b/) (DeepSeek, USD 0.125) · [Gemma 4 26B A4B](https://broadrouter.com/llm-api-pricing/gemma-4-26b-a4b-it/) (Google, USD 0.1375) · [GPT-5 Nano](https://broadrouter.com/llm-api-pricing/gpt-5-nano/) (OpenAI, USD 0.1375).

## Compare Qwen3 32B FP8 with

-   [Gemma 4 26B A4B vs Qwen3 32B](https://broadrouter.com/llm-api-pricing/compare/gemma-4-26b-a4b-it-vs-qwen3-32b/): API price side by side
-   [Qwen3.5 27B vs Qwen3 32B](https://broadrouter.com/llm-api-pricing/compare/qwen3.5-27b-vs-qwen3-32b/): API price side by side
-   [Qwen3 32B vs Qwen3 30B A3B](https://broadrouter.com/llm-api-pricing/compare/qwen3-32b-vs-qwen3-30b-a3b/): API price side by side
-   [Qwen3 235B A22B vs Qwen3 32B](https://broadrouter.com/llm-api-pricing/compare/qwen3-235b-a22b-vs-qwen3-32b/): API price side by side

Also compared: [vs Gemma 4 26B A4B](https://broadrouter.com/llm-api-pricing/compare/gemma-4-26b-a4b-it-vs-qwen3-32b/) · [vs Qwen3.5 27B](https://broadrouter.com/llm-api-pricing/compare/qwen3.5-27b-vs-qwen3-32b/) · [vs Qwen3 30B A3B (fp8)](https://broadrouter.com/llm-api-pricing/compare/qwen3-32b-vs-qwen3-30b-a3b/) · [vs Qwen3 235B A22B FP8](https://broadrouter.com/llm-api-pricing/compare/qwen3-235b-a22b-vs-qwen3-32b/).

[Every Qwen3 32B FP8 price comparison](https://broadrouter.com/llm-api-pricing/compare/#m-qwen3-32b) · [All model-vs-model price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

[All 431 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the Qwen3 32B FP8 API cost per token?

From USD 0.08 per 1M input tokens (USD 0.00000008 per token) and USD 0.28 per 1M output tokens (USD 0.00000028 per token) at the lowest standard prices we found. The median of 5 standard prices is USD 0.102 input and USD 0.57 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for Qwen3 32B FP8?

Among the 5 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.13 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does Qwen sell Qwen3 32B FP8 on its own API?

Qwen publishes no price for Qwen3 32B FP8 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is DeepInfra at USD 0.08 / USD 0.28 per 1M tokens.

### Does Qwen3 32B FP8 have cached input pricing?

1 of 5 standard prices includes one. The lowest is USD 0.0816 per 1M at Featherless. Providers without one bill cached input at the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

### What is the Qwen3 32B FP8 context window?

Up to 131,072 tokens. 3 standard prices come with less, down to 32,768 tokens (Featherless, GMI Cloud and DeepInfra). Check the context column before you pick the cheapest row for long prompts. [Context window calculator](https://broadrouter.com/tools/context-window-calculator/).

### How much does a coding agent cost per month on Qwen3 32B FP8?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 169.20 a month at DeepInfra, USD 234.00 at the median price and USD 324.00 at Amazon Bedrock. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=qwen3-32b).

### Is there a batch, flex or priority price for Qwen3 32B FP8?

Yes: batch from Amazon Bedrock at USD 0.075 / USD 0.30; flex / spot from DeepInfra at USD 0.064 / USD 0.224; priority from DeepInfra at USD 0.12 / USD 0.42 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

### Is Qwen3 32B FP8 free to use through an API?

No provider in our data lists a free price for Qwen3 32B FP8 as of 2026-11-15. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

### Is Qwen3 32B FP8 open source, with open weights, and what is its licence?

Qwen publishes the weights on Hugging Face as [`Qwen/Qwen3-32B`](https://huggingface.co/Qwen/Qwen3-32B), in a public repository with no access gate. The licence, as the [Qwen model card metadata](https://huggingface.co/Qwen/Qwen3-32B) states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Qwen's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

### How many parameters does Qwen3 32B FP8 have?

Total parameters, as the [Qwen model card](https://huggingface.co/Qwen/Qwen3-32B) states them: 32.8B. (checked 2026-11-16; BroadNet did not verify these figures.)

### Does Qwen3 32B FP8 support tool calling?

Yes, according to the [Qwen model card](https://huggingface.co/Qwen/Qwen3-32B): “Qwen3 excels in tool calling capabilities.” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.

### How do I call Qwen3 32B FP8 with the OpenAI SDK?

BroadNet does not serve Qwen3 32B FP8. Use the OpenAI-compatible base URL of a provider that lists it: create the client with `OpenAI(base_url=..., api_key=...)` and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: [DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/) (`https://api.deepinfra.com/v1/openai`, model `Qwen/Qwen3-32B`). Each provider page quotes the provider's docs with a check date.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-qwen3-32b&utm_content=page-cta) ·

**Sources**

-   [Amazon Bedrock: pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/Qwen/Qwen3-32B)
-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/models/Qwen/Qwen3-32B)
-   [GMI Cloud: pricing (checked 2026-11-15)](https://console.gmicloud.ai/model/llm/qwen3-32b-fp8/ae9cad4b-9b87-4b80-99e2-4a73f5715a87)
-   [SiliconFlow: pricing (checked 2026-11-14)](https://www.siliconflow.com/pricing)
