Qwen3.5 9B API pricing
Updated
Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 tie for the lowest blended standard price for Qwen3.5 9B; DeepInfra charges USD 0.10 per 1M input tokens and USD 0.15 per 1M output tokens. The median across 4 standard prices is USD 0.135 / USD 0.20. Each price is read from the provider's own pricing page.
Does Qwen sell Qwen3.5 9B directly?
Qwen publishes no price for Qwen3.5 9B on its own API that we could find, so this page compares hosts only.
Qwen3.5 9B model facts
Facts from Qwen's model card for Qwen/Qwen3.5-9B 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/Qwen3.5-9B) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 4 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | Qwen model card metadata, checked 2026-11-16Quote“license: apache-2.0” |
| Parameters in the weight files (Hugging Face count, not the maker's figure) | About 9.7 billion (9,653,104,368) | Hugging Face model API, checked 2026-11-16Quote“"safetensors": { "total": 9653104368 }” |
| Context length | 262,144 tokens natively, extensible up to 1,010,000 | Qwen model card, checked 2026-11-16Quote“Context Length: 262,144 natively and extensible up to 1,010,000 tokens.” |
| Input and output | Image and text in, text out (the card's task tag is image-text-to-text) | Qwen model card metadata, checked 2026-11-16Quote“pipeline_tag: image-text-to-text” |
| Tool calling | Yes | Qwen model card, checked 2026-11-16Quote“Tool Use: To support tool use, you can use the following command.” |
| First published on Hugging Face (not necessarily the release date) | 2026-02-27 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-02-27T12:58:26.000Z"” |
Qwen3.5 9B 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 69% 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 | DeepInfra tied cheapestQwen/Qwen3.5-9BNotes and source quote“$0.10 in $0.15 out / 1M tokens” | USD 0.10 | not published | USD 0.15 | USD 0.1125 | 262,144 | BFLOAT16 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | SiliconFlow tied cheapestNotes and source quoteContext shown as 262K. “Qwen3.5-9B 262K $0.1 $0.15” | USD 0.10 | not published | USD 0.15 | USD 0.1125 | 262,144 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | FeatherlessQwen/Qwen3.5-9BNotes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). No cached price published. “PRICING: INPUT $0.17 / OUTPUT $0.25” | USD 0.17 | not published | USD 0.25 | USD 0.19 | 32,768 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 4 | Together AINotes and source quote“Qwen3.5 9B $0.17 $0.25” | USD 0.17 | not published | USD 0.25 | USD 0.19 | not stated | not stated | Together AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotQwen/Qwen3.5-9BNotes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.08 $0.12” | USD 0.08 | not published | USD 0.12 | USD 0.09 | 262,144 | BFLOAT16 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra priorityQwen/Qwen3.5-9BNotes and source quotePriority service tier (1.5× standard). “Priority (1.5×) $0.15 $0.225” | USD 0.15 | not published | USD 0.225 | USD 0.1687 | 262,144 | BFLOAT16 | 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 Qwen3.5 9B 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) |
|---|---|---|---|
| DeepInfra | USD 11.70 | USD 26.25 | USD 193.50 |
| SiliconFlow | USD 11.70 | USD 26.25 | USD 193.50 |
| Featherless | USD 19.80 | USD 44.55 | exceeds context |
| Together AI | USD 19.80 | USD 44.55 | USD 328.50 |
For the support chatbot, the cheapest price (DeepInfra and 1 other, tied, USD 11.70 a month) saves USD 4.05 against the median (USD 15.75). For the coding agent the gap is USD 67.50 a month (26% lower).
Which Qwen3.5 9B provider is cheapest for your traffic?
DeepInfra and SiliconFlow share the lowest input price (USD 0.10) and the lowest output price (USD 0.15), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| DeepInfra (no cache price) | USD 0.1125 cheapest | USD 0.1125 cheapest | USD 0.1125 cheapest |
| SiliconFlow (no cache price) | USD 0.1125 cheapest | USD 0.1125 cheapest | USD 0.1125 cheapest |
| Featherless (no cache price) | USD 0.19 | USD 0.19 | USD 0.19 |
| Together AI (no cache price) | USD 0.19 | USD 0.19 | USD 0.19 |
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 4 providers publishes a cached-input discount for Qwen3.5 9B, so cache hits do not change the ranking.
Context windows differ: 262,144 tokens at DeepInfra and SiliconFlow; 32,768 tokens at Featherless. Together AI does not state one. The cheapest row is not always the one that fits a long prompt.
What does Qwen3.5 9B cost in other languages?
The same text needs a different number of tokens in each language. With the Qwen3.8 27B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Qwen3.5 9B:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.022 | DeepInfra |
| Arabic MSA | USD 0.031 | DeepInfra |
| Hindi | USD 0.042 | DeepInfra |
| Chinese | USD 0.058 | DeepInfra |
| Code | USD 0.028 | DeepInfra |
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 Qwen3.5 9B preloaded: your traffic and cache rate, against any of 428 models.
- Qwen 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 Qwen3.5 9B compare with other Qwen models?
The Qwen models whose cheapest standard price is closest to Qwen3.5 9B's (USD 0.1125 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Qwen3 30B A3B (fp8) | USD 0.051 | USD 0.335 | 40,960 | 3 |
| 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 |
| Qwen3-30B-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: DeepSeek V4 Flash (DeepSeek, USD 0.1125) · GLM 5.3 Flash (Z.ai, USD 0.1187) · Mistral Small 3.2 24B Instruct (Mistral AI, USD 0.1062).
Compare Qwen3.5 9B with
- Qwen3.5 9B vs Qwen3-8B: API price side by side
- Qwen3.5 27B vs Qwen3.5 9B: API price side by side
Also compared: vs Qwen3-8B · vs Qwen3.5 27B.
Every Qwen3.5 9B price comparison · All model-vs-model price comparisons
All 428 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 Qwen3.5 9B API cost per token?
From USD 0.10 per 1M input tokens (USD 0.0000001 per token) and USD 0.15 per 1M output tokens (USD 0.00000015 per token) at the lowest standard prices we found. The median of 4 standard prices is USD 0.135 input and USD 0.20 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Qwen3.5 9B?
Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 are tied for the lowest price: DeepInfra and SiliconFlow, each USD 0.1125 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.10 (DeepInfra and 1 other, tied); for output alone, USD 0.15 (DeepInfra and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Qwen sell Qwen3.5 9B on its own API?
Qwen publishes no price for Qwen3.5 9B 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 0.10 / USD 0.15 per 1M tokens.
Does Qwen3.5 9B have cached input pricing?
None of the 4 standard prices includes a cached-input price, so budget repeated prompts at the full input price.
What is the Qwen3.5 9B context window?
Up to 262,144 tokens. 1 standard price comes with less, down to 32,768 tokens (Featherless). 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 Qwen3.5 9B?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 193.50 a month at DeepInfra, USD 261.00 at the median price and USD 328.50 at Together AI. Try your own numbers.
Is there a batch, flex or priority price for Qwen3.5 9B?
Yes: flex / spot from DeepInfra at USD 0.08 / USD 0.12; priority from DeepInfra at USD 0.15 / USD 0.225 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 Qwen3.5 9B free to use through an API?
No provider in our data lists a free price for Qwen3.5 9B 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 Qwen3.5 9B open source, with open weights, and what is its licence?
Qwen publishes the weights on Hugging Face as Qwen/Qwen3.5-9B, 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 Qwen3.5 9B have?
Qwen's model card does not state a total that we found. Hugging Face counts about 9.7 billion (9,653,104,368) parameters in the published weight files of Qwen/Qwen3.5-9B. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).
Does Qwen3.5 9B support tool calling?
Yes, according to the Qwen model card: “Tool Use: To support tool use, you can use the following command.” (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 Qwen3.5 9B with the OpenAI SDK?
BroadNet does not serve Qwen3.5 9B. 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/Qwen3.5-9B) and Together AI (https://api.together.ai/v1). Each provider page quotes the provider's docs with a check date.