BroadRouter

Featherless API pricing

Updated

Featherless lists standard prices for 87 models. The cheapest is Gemma 3 4B at USD 0.05 input and USD 0.10 output per 1M tokens; the dearest is Llama 3 Instruct (70B) at USD 3.50 / USD 8.30. It publishes cached-input prices for 52 of them, and lists no per-model batch, flex or priority prices on the pages we read.

Featherless hosts models it does not train. By maker: Qwen 21, DeepSeek 15, Meta 8, Moonshot AI 8, Z.ai 8, MiniMax 6, and 8 more. 87 prices, each read from Featherless' own pricing page or one of 86 linked model pages, checked 2026-11-15. BroadRouter is BroadNet's own site and does not sell Featherless' services. Automated re-check 2026-11-16: 87 of 87 prices still matched the provider's page.

Models with a standard price
87
Median input / output
USD 0.295 / USD 1.10
Cached-input prices
52 of 87
Cheapest host for
13 of 86 shared models

Which models is Featherless the cheapest provider for?

Of the 86 models that Featherless and at least one other provider both price at the standard tier, Featherless has the lowest price for 13, ranked on a blend of 3 input tokens to 1 output token (5 of them tied with another provider at the same price). It also ties the lowest price for 6 more, where another provider is listed first. It is the dearest for 28. Another 1 model has a standard price from Featherless only.

Models where Featherless is the cheapest provider
ModelFeatherless input / outputNext cheapestSaving on 3:1 blendProviders
Qwen3.8 2.4T A95BUSD 1 / USD 4Alibaba Cloud USD 2 / USD 642%6
DeepSeek R1 0528USD 0.385 / USD 1.625DeepInfra USD 0.50 / USD 2.1524%5
Qwen3 VL 30B A3B InstructUSD 0.15 / USD 0.50DeepInfra USD 0.15 / USD 0.6010%4
MiniMax M2USD 0.2775 / USD 1.11Amazon Bedrock USD 0.30 / USD 1.207%4
Llama 3.2 3B InstructUSD 0.0509 / USD 0.335Cloudflare Workers AI USD 0.051 / USD 0.335under 1%4
Step 5 PreviewUSD 1 / USD 2.70GMI Cloud USD 1 / USD 2.70tie4
Llama 3 8B InstructUSD 0.0925 / USD 0.095Amazon Bedrock USD 0.30 / USD 0.6075%3
Muse Glimmer 30BUSD 0.30 / USD 1.10DeepInfra USD 0.30 / USD 1.205%3
Qwen3 235B A22B Thinking 2507 FP8USD 0.45 / USD 3.50Venice USD 0.45 / USD 3.50tie3
Step 3.7 FlashUSD 0.20 / USD 1.15GMI Cloud USD 0.20 / USD 1.15tie3
L3.1-70B-Euryale-v2.2USD 0.72 / USD 0.72DeepInfra USD 0.85 / USD 0.8515%2
Kimi K2 Instruct 0905USD 0.60 / USD 2.50Novita AI USD 0.60 / USD 2.50tie2
Step-3.5-FlashUSD 0.10 / USD 0.30SiliconFlow USD 0.10 / USD 0.30tie2

The 6 models Featherless sells that the most other providers also sell, with Featherless' rank among them on the 3:1 blend.

Featherless on the most widely hosted models
ModelFeatherlessRankCheapest
GLM 5.3USD 1.40 / USD 4.406 of 24DeepInfra USD 0.5625 / USD 2.50
OpenAI GPT OSS 120BUSD 0.15 / USD 0.6011 of 21CoreWeave Forge USD 0.03 / USD 0.17
GLM 5.3 FlashUSD 0.15 / USD 0.503 of 20GMI Cloud USD 0.075 / USD 0.25
GLM 5.2USD 1.40 / USD 4.405 of 19DeepInfra USD 0.5625 / USD 1.80
Kimi K3USD 2 / USD 102 of 18Chutes USD 1.85 / USD 9.50
DeepSeek V4.1 Flash 1017USD 0.225 / USD 0.903 of 16DeepInfra USD 0.098 / USD 0.294

Which model makers does Featherless sell?

Featherless prices models from 14 makers. Qwen leads with 21 models. Standard prices, USD per 1M input / output tokens.

Featherless models by maker
MakerModelsCheapest modelMedian input / output
Qwen21Qwen3-14B USD 0.12 / USD 0.24USD 0.186 / USD 1.15
DeepSeek15DeepSeek V4 Flash USD 0.14 / USD 0.28USD 0.30 / USD 1
Meta8Llama 3.2 1B Instruct USD 0.027 / USD 0.201USD 0.25 / USD 0.5425
Moonshot AI8Kimi K2 Instruct USD 0.60 / USD 2.50USD 0.80 / USD 3.40
Z.ai8GLM 4.7 Flash USD 0.0653 / USD 0.40USD 0.75 / USD 2.675
MiniMax6MiniMax M3.1 Flash USD 0.15 / USD 0.60USD 0.2975 / USD 1.20
Google5Gemma 3 4B USD 0.05 / USD 0.10USD 0.07 / USD 0.30
Mistral AI4Mistral-Small-24B-Instruct-2501 USD 0.175 / USD 0.29USD 0.2168 / USD 0.34625
OpenAI3GPT OSS 20B USD 0.04 / USD 0.15USD 0.075 / USD 0.30
Sao10K3L3-8B-Lunaris-v1 USD 0.0925 / USD 0.095USD 0.37 / USD 0.38
StepFun3Step-3.5-Flash USD 0.10 / USD 0.30USD 0.20 / USD 1.15
Microsoft1Phi-4 USD 0.07 / USD 0.14—
Tencent1Hy3 USD 1 / USD 4—
Xiaomi1MiMo v2.5 USD 0.149 / USD 0.493—

Featherless price list

USD per 1M tokens: 87 prices for 87 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-15 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Featherless is cheaper. Of 22 hosted model prices with a maker price to compare, 13 are below the maker's and 2 above.

Featherless API prices by model
ModelTierInputCachedOutputContextvs makerSource
DeepSeek R1 0528standardUSD 0.385—USD 1.625131,072—source
DeepSeek R1 Distill Llama 70BstandardUSD 2.60USD 0.52USD 332,768—source
DeepSeek R1 Distill Llama 8BstandardUSD 0.20USD 0.028USD 0.3232,768—source
DeepSeek R1 Distill Qwen 14BstandardUSD 0.431USD 0.0862USD 1.1232,768—source
DeepSeek R1 Distill Qwen 32BstandardUSD 2.72—USD 4.8032,768—source
DeepSeek R1 Distill Qwen 7BstandardUSD 0.68USD 0.136USD 0.8032,768—source
DeepSeek V3 0324standardUSD 0.385—USD 1.625131,072—source
DeepSeek V3.1standardUSD 0.285—USD 1131,072—source
DeepSeek V3.2standardUSD 0.264USD 0.06USD 0.41131,072—source
DeepSeek V4 FlashstandardUSD 0.14USD 0.03USD 0.28262,144—source
DeepSeek V4 Flash 0731standardUSD 0.14USD 0.03USD 0.28262,144—source
DeepSeek V4 ProstandardUSD 1.60USD 0.20USD 3.20262,144+1%source
DeepSeek V4.1 FlashstandardUSD 0.30USD 0.03USD 1.20262,144samesource
DeepSeek V4.1 Flash 1017standardUSD 0.225USD 0.006USD 0.90262,144−25%source
DeepSeek-V3.1-TerminusstandardUSD 0.285—USD 1131,072—source
Gemma 3 12BstandardUSD 0.05—USD 0.1532,768—source
Gemma 3 27BstandardUSD 0.10USD 0.08USD 0.3032,768—source
Gemma 3 4BstandardUSD 0.05—USD 0.1032,768—source
Gemma 4 26B A4BstandardUSD 0.07USD 0.05USD 0.3432,768—source
Gemma 4 31BstandardUSD 0.12USD 0.10USD 0.3632,768—source
GLM 4.6standardUSD 0.55USD 0.11USD 2.20202,752−4%source
GLM 4.7standardUSD 0.55USD 0.11USD 2.20202,752−4%source
GLM 4.7 FlashstandardUSD 0.0653USD 0.0131USD 0.40202,752—source
GLM 5standardUSD 0.95USD 0.19USD 3.15202,752−3%source
GLM 5.1standardUSD 1.30USD 0.26USD 4.30202,752−5%source
GLM 5.2standardUSD 1.40USD 0.15USD 4.40262,144samesource
GLM 5.3standardUSD 1.40USD 0.26USD 4.40262,144samesource
GLM 5.3 FlashstandardUSD 0.15USD 0.03USD 0.50262,144samesource
GPT OSS 20BstandardUSD 0.04—USD 0.15131,072—source
GPT OSS Safeguard 20BstandardUSD 0.075—USD 0.3032,768—source
Hy3standardUSD 1—USD 432,768—source
Kimi K2 InstructstandardUSD 0.60—USD 2.5032,768—source
Kimi K2 Instruct 0905standardUSD 0.60—USD 2.5032,768—source
Kimi K2 ThinkingstandardUSD 0.60—USD 2.5032,768—source
Kimi K2.5standardUSD 0.80USD 0.154USD 3.40262,144—source
Kimi K2.6standardUSD 0.80USD 0.154USD 3.40262,144−15%source
Kimi K2.7 CodestandardUSD 0.80USD 0.154USD 3.40262,144−15%source
Kimi K3standardUSD 2USD 0.30USD 10262,144−33%source
Kimi K3.1 ProstandardUSD 2USD 0.20USD 10262,144samesource
L3-8B-Lunaris-v1standardUSD 0.0925USD 0.074USD 0.0958,192—source
L3.1-70B-Euryale-v2.2standardUSD 0.72—USD 0.7232,768—source
Llama 3 8B InstructstandardUSD 0.0925USD 0.074USD 0.0958,192—source
Llama 3 8B Stheno V3.2standardUSD 0.37USD 0.074USD 0.388,192—source
Llama 3 Instruct (70B)standardUSD 3.50USD 0.70USD 8.308,192—source
Llama 3.1 8B InstructstandardUSD 0.20USD 0.028USD 0.3232,768—source
Llama 3.1 Instruct (70B)standardUSD 2.88—USD 2.8832,768—source
Llama 3.2 1B InstructstandardUSD 0.027—USD 0.20132,768—source
Llama 3.2 3B InstructstandardUSD 0.0509—USD 0.33532,768—source
Llama 3.3 70BstandardUSD 0.65USD 0.52USD 0.7532,768—source
MiMo v2.5standardUSD 0.149USD 0.028USD 0.49332,768—source
MiniMax M2standardUSD 0.2775USD 0.0555USD 1.11204,800—source
Minimax M2.1standardUSD 0.30USD 0.06USD 1.20204,800—source
MiniMax M2.5standardUSD 0.295USD 0.059USD 1.20204,800—source
MiniMax M2.7standardUSD 0.30USD 0.06USD 1.20204,800—source
MiniMax M3standardUSD 0.55USD 0.06USD 2.20262,144+83%source
MiniMax M3.1 FlashstandardUSD 0.15USD 0.015USD 0.601,048,576samesource
Mistral Small 3.1 24B InstructstandardUSD 0.2168—USD 0.402532,768—source
Mistral Small 3.2 24B InstructstandardUSD 0.2168—USD 0.402532,768—source
Mistral-Nemo-Instruct-2407standardUSD 0.2175USD 0.20USD 0.247532,768—source
Mistral-Small-24B-Instruct-2501standardUSD 0.175USD 0.04USD 0.2932,768—source
Muse Glimmer 30BstandardUSD 0.30USD 0.04USD 1.10131,072—source
OpenAI GPT OSS 120BstandardUSD 0.15USD 0.02USD 0.60131,072—source
Phi-4standardUSD 0.07—USD 0.1432,768—source
Qwen 2.5 7BstandardUSD 0.17USD 0.136USD 0.2032,768—source
Qwen2.5 Coder 32B InstructstandardUSD 0.68—USD 1.2032,768—source
Qwen2.5-72B-InstructstandardUSD 0.37—USD 0.4032,768—source
Qwen3 235B A22B FP8standardUSD 0.455—USD 1.8232,768—source
Qwen3 235B A22B Thinking 2507 FP8standardUSD 0.45—USD 3.5032,768—source
Qwen3 32B FP8standardUSD 0.102USD 0.0816USD 0.49332,768—source
Qwen3 Coder 30B A3BstandardUSD 0.125—USD 0.4532,768—source
Qwen3 Coder 480B A35BstandardUSD 0.38USD 0.076USD 1.5532,768—source
Qwen3 Coder NextstandardUSD 0.16USD 0.036USD 1.1532,768—source
Qwen3 Next 80B A3B InstructstandardUSD 0.125—USD 1.1532,768—source
Qwen3 VL 30B A3B InstructstandardUSD 0.15—USD 0.50131,072—source
Qwen3-14BstandardUSD 0.12—USD 0.2432,768—source
Qwen3-30B-A3B-Instruct-2507standardUSD 0.125—USD 0.45262,144—source
Qwen3-8BstandardUSD 0.117—USD 0.45532,768—source
Qwen3.5 27BstandardUSD 0.30—USD 2.4032,768samesource
Qwen3.5 397B A17BstandardUSD 0.55—USD 3.50262,144−5%source
Qwen3.5 9BstandardUSD 0.17—USD 0.2532,768—source
Qwen3.6 27BstandardUSD 0.32USD 0.064USD 2.7032,768−32%source
Qwen3.6 35B A3BstandardUSD 0.186USD 0.032USD 1.113832,768−50%source
Qwen3.8 2.4T A95BstandardUSD 1—USD 4262,144−42%source
Qwen3.8 27BstandardUSD 0.40USD 0.15USD 3262,144−7%source
Step 3.7 FlashstandardUSD 0.20USD 0.04USD 1.15262,144—source
Step 5 PreviewstandardUSD 1USD 0.10USD 2.70262,144—source
Step-3.5-FlashstandardUSD 0.10—USD 0.30262,144—source
  • Cached "—" means Featherless' page shows no cache price for that row; budget cached tokens at the input price.

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

What service tiers does Featherless publish?

Standard prices only: Featherless publishes no per-model batch, flex, priority or fast price on the pages we read.

Cached input: 52 of 87 standard prices include a cache-read price, a median 20% of the input price. What cached input means.

What we recorded about Featherless' pricing page: Featherless sells flat-rate plans (Chat, 25 USD a month, unlimited tokens, human use only) and a per-token Developer plan ("Billed per token", credits from 50 USD a month; "Rates are per model"). Rows are the per-token Developer-plan rates shown on each model's page (featherless.ai/models/<id>); context is the context_length in Featherless's public model API (api.featherless.ai/v1/models/<id>), which matches the page's "Context size". Featherless hosts 50,000+ Hugging Face models; only the original releases of models other providers also serve are listed, plus three Sao10K fine-tunes already tracked. Embedding, TTS and OCR models excluded.

Is Featherless cheaper than the model makers' own APIs?

Mostly yes. Of 22 standard prices for models whose maker sells its own API, 13 are below the maker's price, 2 above and 7 the same, on the 3:1 blend. The median difference is 4% below the maker. The biggest saving is Qwen3.6 35B A3B, 50% below Alibaba Cloud. The biggest markup is MiniMax M3, 83% above MiniMax.

BroadNet Inference and Featherless

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 4 models that Featherless prices: BroadNet Gemma 4 VL 26B at USD 0.10 / USD 0.22 against Featherless' USD 0.07 / USD 0.34 (BroadNet is cheaper on the 3:1 blend); DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Featherless' USD 0.30 / USD 1.20 (BroadNet is cheaper on the 3:1 blend); Qwen3.8 27B at USD 0.175 / USD 2.17 against Featherless' USD 0.40 / USD 3 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Featherless' USD 1.40 / USD 4.40 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on Featherless

Questions

How much does the Featherless API cost per token?

Featherless' standard prices run from USD 0.05 input and USD 0.10 output per 1M tokens (Gemma 3 4B) to USD 3.50 / USD 8.30 (Llama 3 Instruct (70B)). The median across 87 standard prices is USD 0.295 input and USD 1.10 output per 1M, which is USD 0.000000295 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Featherless?

Gemma 3 4B, at USD 0.05 input and USD 0.10 output per 1M tokens (USD 0.0625 on a 3:1 input-to-output blend). The cheapest from other makers: Qwen3-14B (Qwen) at USD 0.12 / USD 0.24; DeepSeek V4 Flash (DeepSeek) at USD 0.14 / USD 0.28; Llama 3.2 1B Instruct (Meta) at USD 0.027 / USD 0.201.

Is Featherless cheaper than other providers?

It depends on the model. Of 86 models that other providers also price, Featherless is the cheapest standard price for 13 (5 of them tied with another provider), for example Qwen3.8 2.4T A95B, DeepSeek R1 0528 and Qwen3 VL 30B A3B Instruct; it ties the lowest price, without beating it, for 6 more; another provider is cheaper for 67; and it is the dearest for 28. Its median rank is 2 of a median 4 providers, on a 3:1 input-to-output blend.

Does Featherless have batch, cached or priority pricing?

Cached input: yes, for 52 of 87 standard prices, at a median 20% of the input price. No batch, flex or priority prices are listed per model on the pages we read.

How much does a chatbot cost per month on Featherless?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 6.05 on Llama 3.2 1B Instruct, USD 34.02 on DeepSeek V4.1 Flash (the middle of Featherless' list) and USD 331.20 on DeepSeek R1 Distill Qwen 32B. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity