BroadRouter

Qwen3 Coder 480B A35B API pricing

Updated

The cheapest standard price for Qwen3 Coder 480B A35B is SiliconFlow at USD 0.25 per 1M input tokens and USD 1 per 1M output tokens. The median across 6 standard prices is USD 0.325 / USD 1.525. Every price is read from the provider's own pricing page, checked 2026-11-15.

Qwen · slug qwen3-coder · up to 262,144 tokens of context · 6 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 (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

Does Qwen sell Qwen3 Coder 480B A35B directly?

Qwen publishes no price for Qwen3 Coder 480B A35B on its own API that we could find, so this page compares hosts only.

Qwen3 Coder 480B A35B 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 4.1× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Qwen3 Coder 480B A35B API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1SiliconFlow cheapest
Notes and source quote

Context shown as 262K.

“Qwen3-Coder-480B-A35B 262K $0.25 $nan $1.0”
USD 0.25not publishedUSD 1USD 0.4375262,144not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
2DeepInfra
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
Notes and source quote

DeepInfra Turbo variant (quantized).

“$0.30 in $1.00 out $0.10 cached / 1M tokens”
USD 0.30USD 0.10USD 1USD 0.475262,144FP4DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
3Google Vertex AI
qwen3-coder-480b-a35b-instruct
Notes and source quote
“Qwen3-Coder-480B-A35B-Instruct Input $0.22 … Output $1.80 … Cache Hit $0.022”
USD 0.22USD 0.022USD 1.80USD 0.615not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
4Venice
qwen3-coder-480b-a35b-instruct-turbo
Notes and source quote
“| Qwen 3 Coder 480B Turbo | `qwen3-coder-480b-a35b-instruct-turbo` | $0.35 | $1.50 | $0.04 | — | Private |”
USD 0.35USD 0.04USD 1.50USD 0.6375256,000FP8Venice page
checked 2026-11-15
re-checked 2026-11-16
5Featherless
Qwen/Qwen3-Coder-480B-A35B-Instruct
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.38 / CACHED $0.076 / OUTPUT $1.55”
USD 0.38USD 0.076USD 1.55USD 0.672532,768FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
6GMI Cloud
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Notes and source quote

Long-prompt tier: prompts over 32,000 tokens cost 1.62 in / 8.1 out.

“Price ≤ 32k token Input $0.90 Output $4.50 Cache Read $0.18 Cache Write - 32k - 128k token Input $1.62 Output $8.10 > 128k token Input $2.70 Output $13.50”
USD 0.90USD 0.18USD 4.50USD 1.80262,128FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
—Google Vertex AI batch
qwen3-coder-480b-a35b-instruct
Notes and source quote
“Qwen3-Coder-480B-A35B-Instruct Batch Input $0.11 … Batch Output $0.90”
USD 0.11not publishedUSD 0.90USD 0.3075not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
Notes and source quote

Flex service tier (0.8× standard). DeepInfra Turbo variant (quantized).

“Flex (0.8×) $0.24 $0.80 $0.08”
USD 0.24USD 0.08USD 0.80USD 0.38262,144FP4DeepInfra page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Qwen3 Coder 480B A35B 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.
Monthly cost of three workloads on Qwen3 Coder 480B A35B, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
SiliconFlowUSD 40.50USD 75.00USD 540.00
DeepInfraUSD 34.20USD 72.60USD 324.00
Google Vertex AIUSD 41.51USD 65.54USD 255.06
VeniceUSD 41.76USD 84.18USD 290.70
FeatherlessUSD 45.68USD 92.56exceeds context
GMI CloudUSD 123.12USD 231.66USD 923.40

For the support chatbot, the cheapest price (DeepInfra, USD 34.20 a month) saves USD 7.43 against the median (USD 41.63). For the coding agent the gap is USD 86.13 a month (25% lower). The winner changes with the workload: Google Vertex AI wins the cache-heavy agent, DeepInfra the chatbot.

Which Qwen3 Coder 480B A35B provider is cheapest for your traffic?

Google Vertex AI has the lowest input price (USD 0.22) and SiliconFlow the lowest output price (USD 1). They cost the same at 27 input tokens per output token. With more input than that, as with long prompts or retrieval, Google Vertex AI is cheaper; with less, as with long answers, SiliconFlow is.

Qwen3 Coder 480B A35B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
SiliconFlow (no cache price)USD 0.4375 cheapestUSD 0.4375USD 0.4375
DeepInfraUSD 0.475USD 0.40 cheapestUSD 0.34 cheapest
Google Vertex AIUSD 0.615USD 0.5408USD 0.4814
VeniceUSD 0.6375USD 0.5212USD 0.4283
FeatherlessUSD 0.6725USD 0.5585USD 0.4673
GMI CloudUSD 1.80USD 1.53USD 1.314

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.

5 of 6 providers publish a cached-input price below the input price: DeepInfra (67% off), Google Vertex AI (90% off), Venice (89% off), Featherless (80% off), GMI Cloud (80% off). SiliconFlow publishes none, so cached tokens there bill at the input price.

Context windows differ: 262,144 tokens at SiliconFlow and DeepInfra; 262,128 tokens at GMI Cloud; 256,000 tokens at Venice; 32,768 tokens at Featherless. Google Vertex AI does not state one. The cheapest row is not always the one that fits a long prompt.

What does Qwen3 Coder 480B A35B 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 Coder 480B A35B:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.048Google Vertex AI
Arabic MSAUSD 0.085Google Vertex AI
HindiUSD 0.205Google Vertex AI
ChineseUSD 0.141Google Vertex AI
CodeUSD 0.057Google Vertex 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

The Qwen models whose cheapest standard price is closest to Qwen3 Coder 480B A35B's (USD 0.4375 blended):

Qwen models priced closest to Qwen3 Coder 480B A35B
ModelCheapest inputCheapest outputMax contextProviders
Qwen3 Next 80B A3B ThinkingUSD 0.15USD 1.20262,1442
Qwen3 235B A22B FP8USD 0.17USD 1.0932,7682
Qwen-MT PlusUSD 0.25USD 0.7516,3842
Qwen2.5-72B-InstructUSD 0.36USD 0.4032,7683
Qwen3 VL 235B A22BUSD 0.20USD 0.88262,1443
Qwen3.5 35B A3BUSD 0.14USD 1262,1447

Priced closest from other makers: DeepSeek V3 (DeepSeek, USD 0.4375) · Step 3.7 Flash (StepFun, USD 0.4375) · MiniMax M2.5 (MiniMax, USD 0.44).

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 Coder 480B A35B API cost per token?

From USD 0.22 per 1M input tokens (USD 0.00000022 per token) and USD 1 per 1M output tokens (USD 0.000001 per token) at the cheapest standard price, which can come from different providers. The median of 6 standard prices is USD 0.325 input and USD 1.525 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 Coder 480B A35B?

SiliconFlow, ranked on a blend of 3 input tokens to 1 output token (USD 0.4375 per 1M). For input alone the lowest price is USD 0.22 (Google Vertex AI); for output alone, USD 1 (SiliconFlow and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Qwen sell Qwen3 Coder 480B A35B on its own API?

Qwen publishes no price for Qwen3 Coder 480B A35B on its own API that we could find, so there is no maker price to compare. The cheapest host is SiliconFlow at USD 0.25 / USD 1 per 1M tokens.

Does Qwen3 Coder 480B A35B have cached input pricing?

5 of 6 standard prices include one. The lowest is USD 0.022 per 1M at Google Vertex AI; the median is USD 0.076. Providers without one bill cached input at the input price. What cached input means.

What is the Qwen3 Coder 480B A35B context window?

Up to 262,144 tokens. 3 standard prices come with less, down to 32,768 tokens (Featherless, Venice and 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 Coder 480B A35B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 255.06 a month at Google Vertex AI, USD 341.19 at the median price and USD 923.40 at GMI Cloud. Try your own numbers.

Is there a batch, flex or priority price for Qwen3 Coder 480B A35B?

Yes: batch from Google Vertex AI at USD 0.11 / USD 0.90; flex / spot from DeepInfra at USD 0.24 / USD 0.80 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 Coder 480B A35B free to use through an API?

No provider in our data lists a free price for Qwen3 Coder 480B A35B as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity