Qwen3 30B A3B (fp8) API pricing
Updated
Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Qwen3 30B A3B (fp8) is Cloudflare Workers AI at USD 0.051 per 1M input tokens and USD 0.335 per 1M output tokens. The median across 3 standard prices is USD 0.08 / USD 0.335. Each price is read from the provider's own pricing page.
Does Qwen sell Qwen3 30B A3B (fp8) directly?
Qwen publishes no price for Qwen3 30B A3B (fp8) on its own API that we could find, so this page compares hosts only.
Qwen3 30B A3B (fp8) model facts
Facts from Qwen's model card for Qwen/Qwen3-30B-A3B 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.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (Qwen/Qwen3-30B-A3B) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 16 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | Qwen model card metadata, checked 2026-11-16Quote“license: apache-2.0” |
| Total parameters | 30.5B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 30.5B in total and 3.3B activated” |
| Active parameters per token | 3.3B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 30.5B in total and 3.3B activated” |
| Context length | 32,768 tokens natively; 131,072 tokens with YaRN | Qwen model card, checked 2026-11-16Quote“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, checked 2026-11-16Quote“pipeline_tag: text-generation” |
| Tool calling | Yes | Qwen model card, checked 2026-11-16Quote“Qwen3 excels in tool calling capabilities.” |
| First published on Hugging Face (not necessarily the release date) | 2025-04-27 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2025-04-27T03:43:05.000Z"” |
Qwen3 30B A3B (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 76% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Cloudflare Workers AI cheapest@cf/qwen/qwen3-30b-a3b-fp8Notes and source quoteCloudflare publishes this USD per-token price alongside the neuron price. “@cf/qwen/qwen3-30b-a3b-fp8 $0.051 per M input tokens $0.335 per M output tokens” | USD 0.051 | not published | USD 0.335 | USD 0.122 | not stated | FP8 | Cloudflare Workers AI page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | GMI CloudQwen/Qwen3-30B-A3BNotes and source quoteNo cache-read price published. “Price (per 1M tokens) Input $0.08 Output $0.25” | USD 0.08 | not published | USD 0.25 | USD 0.1225 | 40,946 | BF16 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | DeepInfraQwen/Qwen3-30B-A3BNotes and source quote“$0.12 in $0.50 out / 1M tokens” | USD 0.12 | not published | USD 0.50 | USD 0.215 | 40,960 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotQwen/Qwen3-30B-A3BNotes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.096 $0.40” | USD 0.096 | not published | USD 0.40 | USD 0.172 | 40,960 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra priorityQwen/Qwen3-30B-A3BNotes and source quotePriority service tier (1.5× standard). “Priority (1.5×) $0.18 $0.75” | USD 0.18 | not published | USD 0.75 | USD 0.3225 | 40,960 | FP8 | DeepInfra page 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 (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 (email to info@broadnet.ai, with this page's link filled in).
What does Qwen3 30B A3B (fp8) cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. 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.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Cloudflare Workers AI | USD 10.62 | USD 17.26 | USD 121.95 |
| GMI Cloud | USD 11.70 | USD 22.95 | exceeds context |
| DeepInfra | USD 19.80 | USD 36.30 | exceeds context |
For the support chatbot, the cheapest price (Cloudflare Workers AI, USD 10.62 a month) saves USD 1.08 against the median (USD 11.70). For the coding agent the gap is USD 44.55 a month (27% lower).
Which Qwen3 30B A3B (fp8) provider is cheapest for your traffic?
Cloudflare Workers AI has the lowest input price (USD 0.051) and GMI Cloud the lowest output price (USD 0.25). They cost the same at 2.9 input tokens per output token. With more input than that, as with long prompts or retrieval, Cloudflare Workers AI is cheaper; with less, as with long answers, GMI Cloud is.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Cloudflare Workers AI (no cache price) | USD 0.122 cheapest | USD 0.122 cheapest | USD 0.122 cheapest |
| GMI Cloud (no cache price) | USD 0.1225 | USD 0.1225 | USD 0.1225 |
| DeepInfra (no cache price) | USD 0.215 | USD 0.215 | USD 0.215 |
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.
None of the 3 providers publishes a cached-input discount for Qwen3 30B A3B (fp8), so cache hits do not change the ranking.
Context windows differ: 40,960 tokens at DeepInfra; 40,946 tokens at GMI Cloud. Cloudflare Workers AI does not state one. The cheapest row is not always the one that fits a long prompt.
What does Qwen3 30B A3B (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 30B A3B (fp8):
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.011 | Cloudflare Workers AI |
| Arabic MSA | USD 0.020 | Cloudflare Workers AI |
| Hindi | USD 0.047 | Cloudflare Workers AI |
| Chinese | USD 0.033 | Cloudflare Workers AI |
| Code | USD 0.013 | Cloudflare Workers AI |
From BroadRouter's real cost by language dataset, 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 30B A3B (fp8) preloaded: your traffic and cache rate, against any of 431 models.
- 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: what a higher cache-hit rate saves.
How does Qwen3 30B A3B (fp8) compare with other Qwen models?
The Qwen models whose cheapest standard price is closest to Qwen3 30B A3B (fp8)'s (USD 0.122 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Qwen3 Coder 30B A3B | USD 0.07 | USD 0.28 | 262,144 | 3 |
| Qwen3-14B | USD 0.07 | USD 0.28 | 131,072 | 3 |
| Qwen3 32B FP8 | USD 0.08 | USD 0.28 | 131,072 | 5 |
| Qwen3.5 9B | USD 0.10 | USD 0.15 | 262,144 | 4 |
| Qwen3-30B-A3B-Instruct-2507 | USD 0.09 | USD 0.30 | 262,144 | 2 |
| Qwen3 235B A22B Instruct 2507 FP8 | USD 0.0875 | USD 0.35 | 262,144 | 5 |
Priced closest from other makers: Llama 3.2 3B Instruct (Meta, USD 0.1219) · DeepSeek R1 Distill Qwen 7B (DeepSeek, USD 0.125) · GLM 5.3 Flash (Z.ai, USD 0.1187).
Compare Qwen3 30B A3B (fp8) with
- Gemma 4 26B A4B vs Qwen3 30B A3B: API price side by side
- Qwen3.5 35B A3B vs Qwen3 30B A3B: API price side by side
- Qwen3-30B-A3B-2507 vs Qwen3 30B A3B: API price side by side
- Qwen3 30B A3B vs Qwen3-14B: API price side by side
- Qwen3 32B vs Qwen3 30B A3B: API price side by side
Also compared: vs Gemma 4 26B A4B · vs Qwen3.5 35B A3B · vs Qwen3-30B-A3B-Instruct-2507 · vs Qwen3-14B · vs Qwen3 32B FP8.
Every Qwen3 30B A3B (fp8) price comparison · All model-vs-model price comparisons
All 431 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Qwen3 30B A3B (fp8) API cost per token?
From USD 0.051 per 1M input tokens (USD 0.000000051 per token) and USD 0.25 per 1M output tokens (USD 0.00000025 per token) at the lowest standard prices we found, which can come from different providers. The median of 3 standard prices is USD 0.08 input and USD 0.335 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 30B A3B (fp8)?
Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Cloudflare Workers AI, ranked on a blend of 3 input tokens to 1 output token (USD 0.122 per 1M). For input alone the lowest price is USD 0.051 (Cloudflare Workers AI); for output alone, USD 0.25 (GMI Cloud). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Qwen sell Qwen3 30B A3B (fp8) on its own API?
Qwen publishes no price for Qwen3 30B A3B (fp8) on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Cloudflare Workers AI at USD 0.051 / USD 0.335 per 1M tokens.
Does Qwen3 30B A3B (fp8) have cached input pricing?
None of the 3 standard prices includes a cached-input price, so budget repeated prompts at the full input price.
What is the Qwen3 30B A3B (fp8) context window?
Up to 40,960 tokens. 1 standard price comes with less, down to 40,946 tokens (GMI Cloud). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Qwen3 30B A3B (fp8)?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 121.95 a month at Cloudflare Workers AI, USD 166.50 at the median price and USD 261.00 at DeepInfra. Try your own numbers.
Is there a batch, flex or priority price for Qwen3 30B A3B (fp8)?
Yes: flex / spot from DeepInfra at USD 0.096 / USD 0.40; priority from DeepInfra at USD 0.18 / USD 0.75 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 30B A3B (fp8) free to use through an API?
No provider in our data lists a free price for Qwen3 30B A3B (fp8) as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is Qwen3 30B A3B (fp8) open source, with open weights, and what is its licence?
Qwen publishes the weights on Hugging Face as Qwen/Qwen3-30B-A3B, in a public repository with no access gate. The licence, as the Qwen model card metadata 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 30B A3B (fp8) have?
Total parameters, as the Qwen model card states them: 30.5B. Active parameters per token: 3.3B. (checked 2026-11-16; BroadNet did not verify these figures.)
Does Qwen3 30B A3B (fp8) support tool calling?
Yes, according to the Qwen model card: “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 30B A3B (fp8) with the OpenAI SDK?
BroadNet does not serve Qwen3 30B A3B (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://api.deepinfra.com/v1/openai, model Qwen/Qwen3-30B-A3B). Each provider page quotes the provider's docs with a check date.