BroadRouter

Qwen3 235B A22B Thinking 2507 FP8 API pricing

Updated

Among the 3 providers we checked (prices read 2026-11-15), 2 tie for the lowest blended standard price for Qwen3 235B A22B Thinking 2507 FP8; Featherless charges USD 0.45 per 1M input tokens and USD 3.50 per 1M output tokens. The median across 3 standard prices is USD 0.45 / USD 3.50. Each price is read from the provider's own pricing page.

Qwen · slug qwen3-235b-a22b-thinking-2507 · up to 131,072 tokens of context · 3 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. Archived list prices since 2025-09-26 (12 archived price points, 2 list-price changes): LLM API price history.

Does Qwen sell Qwen3 235B A22B Thinking 2507 FP8 directly?

Qwen publishes no price for Qwen3 235B A22B Thinking 2507 FP8 on its own API that we could find, so this page compares hosts only.

Qwen3 235B A22B Thinking 2507 FP8 model facts

Facts from Qwen's model card for Qwen/Qwen3-235B-A22B-Thinking-2507 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 235B A22B Thinking 2507 FP8: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (Qwen/Qwen3-235B-A22B-Thinking-2507) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 118 .safetensors files listed”
LicenceApache 2.0 (apache-2.0)Qwen model card metadata, checked 2026-11-16
Quote
“license: apache-2.0”
Total parameters235BQwen model card, checked 2026-11-16
Quote
“Number of Parameters: 235B in total and 22B activated”
Active parameters per token22BQwen model card, checked 2026-11-16
Quote
“Number of Parameters: 235B in total and 22B activated”
Context length262,144 tokens nativelyQwen model card, checked 2026-11-16
Quote
“Context Length: 262,144 natively.”
Input and outputText in, text out (the card's task tag is text-generation)Qwen model card metadata, checked 2026-11-16
Quote
“pipeline_tag: text-generation”
Tool callingYesQwen model card, checked 2026-11-16
Quote
“Qwen3 excels in tool calling capabilities.”
First published on Hugging Face (not necessarily the release date)2025-07-25Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2025-07-25T04:59:05.000Z"”

Qwen3 235B A22B Thinking 2507 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 8% above the cheapest.

Qwen3 235B A22B Thinking 2507 FP8 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Featherless tied cheapest
Qwen/Qwen3-235B-A22B-Thinking-2507
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits). No cached price published.

“PRICING: INPUT $0.45 / OUTPUT $3.5”
USD 0.45not publishedUSD 3.50USD 1.21232,768FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
2Venice tied cheapest
qwen3-235b-a22b-thinking-2507
Notes and source quote
“| Qwen 3 235B A22B Thinking 2507 | `qwen3-235b-a22b-thinking-2507` | $0.45 | $3.50 | — | — | Private |”
USD 0.45not publishedUSD 3.50USD 1.212128,000FP8Venice page
checked 2026-11-15
re-checked 2026-11-16
3GMI Cloud
Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
Notes and source quote

No cache-read price published.

“Price (per 1M tokens) Input $0.35 Output $4.20”
USD 0.35not publishedUSD 4.20USD 1.313131,072FP8GMI Cloud page
checked 2026-11-15
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 235B A22B Thinking 2507 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.
Monthly cost of three workloads on Qwen3 235B A22B Thinking 2507 FP8, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
FeatherlessUSD 103.50USD 160.50exceeds context
VeniceUSD 103.50USD 160.50USD 1,125
GMI CloudUSD 107.10USD 147.00USD 1,008

For the support chatbot, the cheapest price (Featherless and 1 other, tied, USD 103.50 a month) saves USD 0 against the median (USD 103.50). For the coding agent the gap is USD 117.00 a month (10% lower). The winner changes with the workload: GMI Cloud wins the cache-heavy agent, Featherless the chatbot.

Which Qwen3 235B A22B Thinking 2507 FP8 provider is cheapest for your traffic?

GMI Cloud has the lowest input price (USD 0.35) and Featherless and Venice the lowest output price (USD 3.50). They cost the same at 7 input tokens per output token. With more input than that, as with long prompts or retrieval, GMI Cloud is cheaper; with less, as with long answers, Featherless and Venice are.

Qwen3 235B A22B Thinking 2507 FP8: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Featherless (no cache price)USD 1.212 cheapestUSD 1.212 cheapestUSD 1.212 cheapest
Venice (no cache price)USD 1.212 cheapestUSD 1.212 cheapestUSD 1.212 cheapest
GMI Cloud (no cache price)USD 1.313USD 1.313USD 1.313

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 235B A22B Thinking 2507 FP8, so cache hits do not change the ranking.

Context windows differ: 131,072 tokens at GMI Cloud; 128,000 tokens at Venice; 32,768 tokens at Featherless. The cheapest row is not always the one that fits a long prompt.

Estimate your own bill

The Qwen models whose cheapest standard price is closest to Qwen3 235B A22B Thinking 2507 FP8's (USD 1.212 blended):

Qwen models priced closest to Qwen3 235B A22B Thinking 2507 FP8
ModelCheapest inputCheapest outputMax contextProviders
Qwen3.6 PlusUSD 0.50USD 3262,1443
Qwen3.5 397B A17BUSD 0.45USD 3262,1447
Qwen3.8 2.4T A95BUSD 1USD 41,048,5766
Qwen3.7 MaxUSD 1.25USD 3.751,000,0005
Qwen2.5 Coder 32B InstructUSD 0.66USD 132,7682
Qwen3.5 122B A10BUSD 0.26USD 2.08262,1444

Priced closest from other makers: Kimi K2.7 Code (Moonshot AI, USD 1.20) · Hy4 Preview (Tencent, USD 1.251) · DeepSeek V4 Pro 0813 (DeepSeek, USD 1.30).

Compare Qwen3 235B A22B Thinking 2507 FP8 with

Also compared: vs Qwen3 235B A22B Instruct 2507 FP8.

Every Qwen3 235B A22B Thinking 2507 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 235B A22B Thinking 2507 FP8 API cost per token?

From USD 0.35 per 1M input tokens (USD 0.00000035 per token) and USD 3.50 per 1M output tokens (USD 0.0000035 per token) at the lowest standard prices we found, which can come from different providers. The median of 3 standard prices is USD 0.45 input and USD 3.50 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 235B A22B Thinking 2507 FP8?

Among the 3 providers we checked (prices read 2026-11-15), 2 are tied for the lowest price: Featherless and Venice, each USD 1.212 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.35 (GMI Cloud); for output alone, USD 3.50 (Featherless and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Qwen sell Qwen3 235B A22B Thinking 2507 FP8 on its own API?

Qwen publishes no price for Qwen3 235B A22B Thinking 2507 FP8 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Featherless at USD 0.45 / USD 3.50 per 1M tokens.

Does Qwen3 235B A22B Thinking 2507 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 235B A22B Thinking 2507 FP8 context window?

Up to 131,072 tokens. 2 standard prices come with less, down to 32,768 tokens (Featherless and Venice). 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 235B A22B Thinking 2507 FP8?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,008 a month at GMI Cloud, USD 1,125 at the median price and USD 1,125 at Venice. Try your own numbers.

Is Qwen3 235B A22B Thinking 2507 FP8 free to use through an API?

No provider in our data lists a free price for Qwen3 235B A22B Thinking 2507 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 235B A22B Thinking 2507 FP8 open source, with open weights, and what is its licence?

Qwen publishes the weights on Hugging Face as Qwen/Qwen3-235B-A22B-Thinking-2507, 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 235B A22B Thinking 2507 FP8 have?

Total parameters, as the Qwen model card states them: 235B. Active parameters per token: 22B. (checked 2026-11-16; BroadNet did not verify these figures.)

Does Qwen3 235B A22B Thinking 2507 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.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity