BroadRouter

Parasail API pricing

Updated

Parasail lists standard per-token prices on its own pricing page for 39 models. The cheapest is GPT OSS 20B at USD 0.04 input and USD 0.20 output per 1M tokens; the dearest is Kimi K3 at USD 3 / USD 15. It publishes cached-input prices for 38 of them, plus fast prices. Checked 2026-11-14.

Parasail hosts models it does not train. By maker: Qwen 9, Z.ai 5, Moonshot AI 4, DeepSeek 3, Google 3, MiniMax 3, and 8 more. 40 prices, each read from Parasail's own pricing page, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell Parasail's services. Automated re-check 2026-11-16: 40 of 40 prices still matched the provider's page.

Models with a standard price
39
Median input / output
USD 0.25 / USD 1
Cached-input prices
38 of 39
Cheapest host for
1 of 33 shared models

Which models is Parasail the cheapest provider for?

Of the 33 models that Parasail and at least one other provider both price at the standard tier, Parasail has the lowest price for 1, ranked on a blend of 3 input tokens to 1 output token. It also ties the lowest price for 2 more, where another provider is listed first. It is the dearest for 5. Another 6 models have a standard price from Parasail only.

Models where Parasail is the cheapest provider
ModelParasail input / outputNext cheapestSaving on 3:1 blendProviders
Qwen3 Coder NextUSD 0.12 / USD 0.80Featherless USD 0.16 / USD 1.1529%3

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

Parasail on the most widely hosted models
ModelParasailRankCheapest
GLM 5.3USD 1.40 / USD 4.406 of 24DeepInfra USD 0.5625 / USD 2.50
OpenAI GPT OSS 120BUSD 0.10 / USD 0.7511 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 3 / USD 155 of 18Chutes USD 1.85 / USD 9.50
DeepSeek V4.1 FlashUSD 0.30 / USD 1.205 of 16DeepInfra USD 0.14 / USD 0.42

Which model makers does Parasail sell?

Parasail prices models from 14 makers. Qwen leads with 9 models. Standard prices, USD per 1M input / output tokens.

Parasail models by maker
MakerModelsCheapest modelMedian input / output
Qwen9Qwen3 Coder Next USD 0.12 / USD 0.80USD 0.15 / USD 1
Z.ai5GLM 5.3 Flash USD 0.15 / USD 0.50USD 1.40 / USD 4.40
Moonshot AI4Kimi K2.6 USD 0.75 / USD 3.50USD 1.375 / USD 6.75
DeepSeek3DeepSeek V4 Flash USD 0.14 / USD 0.28USD 0.30 / USD 1.20
Google3Gemma 3 27B USD 0.08 / USD 0.45USD 0.13 / USD 0.40
MiniMax3MiniMax M3.1 Flash USD 0.15 / USD 0.60USD 0.30 / USD 1.20
TheDrummer3Cydonia 24B v4.1 USD 0.30 / USD 0.50USD 0.55 / USD 0.80
Meta2Llama 3.3 70B USD 0.22 / USD 0.50USD 0.285 / USD 0.75
OpenAI2GPT OSS 20B USD 0.04 / USD 0.20USD 0.07 / USD 0.475
Arcee AI1Trinity Large (Thinking) USD 0.22 / USD 0.85—
ByteDance1UI-TARS 1.5 7B USD 0.10 / USD 0.20—
Mistral AI1Mistral Small 3.2 24B Instruct USD 0.09 / USD 0.30—
NVIDIA1NVIDIA Nemotron 3 Ultra USD 0.50 / USD 2.50—
Xiaomi1MiMo v2.5 USD 0.14 / USD 0.28—

Parasail price list

USD per 1M tokens: 40 prices for 39 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 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 Parasail is cheaper. Of 16 hosted model prices with a maker price to compare, 5 are below the maker's and 1 above.

Parasail API prices by model
ModelTierInputCachedOutputContextvs makerSource
Cydonia 24B v4.1standardUSD 0.30USD 0.15USD 0.50not stated—source
DeepSeek V4 FlashstandardUSD 0.14USD 0.07USD 0.28not stated—source
DeepSeek V4 ProstandardUSD 1.74USD 0.10USD 3.48not stated+10%source
DeepSeek V4.1 FlashstandardUSD 0.30USD 0.006USD 1.20not statedsamesource
Gemma 3 27BstandardUSD 0.08USD 0.04USD 0.45not stated—source
Gemma 4 26B A4BstandardUSD 0.13USD 0.05USD 0.40not stated—source
Gemma 4 31BstandardUSD 0.15USD 0.06USD 0.40not stated—source
GLM 5standardUSD 1USD 0.20USD 3.20not statedsamesource
GLM 5.1standardUSD 1.40USD 0.26USD 4.40not statedsamesource
GLM 5.2standardUSD 1.40USD 0.26USD 4.40not statedsamesource
GLM 5.3standardUSD 1.40USD 0.26USD 4.40not statedsamesource
GLM 5.3 FlashstandardUSD 0.15USD 0.03USD 0.50not statedsamesource
GPT OSS 20BstandardUSD 0.04USD 0.02USD 0.20not stated—source
Kimi K2.6standardUSD 0.75USD 0.16USD 3.50not stated−16%source
Kimi K2.7 CodestandardUSD 0.75USD 0.16USD 3.50not stated−16%source
Kimi K3standardUSD 3USD 0.30USD 15not statedsamesource
Kimi K3.1 ProstandardUSD 2USD 0.20USD 10not statedsamesource
Llama 3.3 70BstandardUSD 0.22USD 0.11USD 0.50not stated—source
Llama 4 Maverick 17B 128E Instruct FP8standardUSD 0.35USD 0.17USD 1not stated—source
MiMo v2.5standardUSD 0.14USD 0.05USD 0.28not stated—source
MiniMax M2.5standardUSD 0.30USD 0.03USD 1.20not stated—source
MiniMax M3standardUSD 0.30USD 0.06USD 1.20not statedsamesource
MiniMax M3.1 FlashstandardUSD 0.15USD 0.015USD 0.60not statedsamesource
Mistral Small 3.2 24B InstructstandardUSD 0.09USD 0.05USD 0.30not stated—source
NVIDIA Nemotron 3 UltrastandardUSD 0.50USD 0.10USD 2.50not stated—source
OpenAI GPT OSS 120Bstandard
fast
USD 0.10
USD 0.15
USD 0.055
—
USD 0.75
USD 0.60
not stated—source
Qwen2.5-VL 72BstandardUSD 0.80USD 0.40USD 1not stated—source
Qwen3 235B A22B Instruct 2507 FP8standardUSD 0.14USD 0.05USD 0.80not stated—source
Qwen3 Coder NextstandardUSD 0.12USD 0.07USD 0.80not stated—source
Qwen3 Next 80B A3B InstructstandardUSD 0.10USD 0.07USD 1.10not stated—source
Qwen3 VL 235B A22BstandardUSD 0.21USD 0.10USD 1.90not stated—source
Qwen3-VL 8BstandardUSD 0.25USD 0.12USD 0.75not stated—source
Qwen3.5 35B A3BstandardUSD 0.15USD 0.05USD 1not stated−47%source
Qwen3.5 397B A17BstandardUSD 0.50USD 0.30USD 3.60not stated−6%source
Qwen3.6 35B A3BstandardUSD 0.15USD 0.05USD 1not stated−57%source
Skyfall 31B v4.2standardUSD 0.55USD 0.25USD 0.80not stated—source
Skyfall 36B v2 (FP8)standardUSD 0.55USD 0.25USD 0.80not stated—source
Trinity Large (Thinking)standardUSD 0.22USD 0.06USD 0.85not stated—source
UI-TARS 1.5 7BstandardUSD 0.10USD 0.10USD 0.20not stated—source
  • Cached "—" means Parasail's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": Parasail's pricing page does not give context windows.

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

What service tiers does Parasail publish?

  • fast (1 row). Across 1 model with both prices, median fast input is 1.5× standard and median output 20% below standard.

Cached input: 38 of 39 standard prices include a cache-read price, a median 36% of the input price. What cached input means.

What we recorded about Parasail's pricing page: Serverless endpoints table on parasail.io/pricing (columns: input, output, cache read per 1M tokens). The page does not give API model ids or context windows. TTS and embedding rows left out.

Is Parasail cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 16 standard prices for models whose maker sells its own API, 5 are below the maker's price, 1 above and 10 the same, on the 3:1 blend. The median difference is zero. The biggest saving is Qwen3.6 35B A3B, 57% below Alibaba Cloud. The biggest markup is DeepSeek V4 Pro, 10% above DeepSeek.

BroadNet Inference and Parasail

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 3 models that Parasail prices: BroadNet Gemma 4 VL 26B at USD 0.10 / USD 0.22 against Parasail's USD 0.13 / USD 0.40 (BroadNet is cheaper on the 3:1 blend); DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Parasail's USD 0.30 / USD 1.20 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Parasail's 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 Parasail

Questions

How much does the Parasail API cost per token?

Parasail's standard prices run from USD 0.04 input and USD 0.20 output per 1M tokens (GPT OSS 20B) to USD 3 / USD 15 (Kimi K3). The median across 39 standard prices is USD 0.25 input and USD 1 output per 1M, which is USD 0.00000025 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Parasail?

GPT OSS 20B, at USD 0.04 input and USD 0.20 output per 1M tokens (USD 0.08 on a 3:1 input-to-output blend). The cheapest from other makers: Qwen3 Coder Next (Qwen) at USD 0.12 / USD 0.80; GLM 5.3 Flash (Z.ai) at USD 0.15 / USD 0.50; Kimi K2.6 (Moonshot AI) at USD 0.75 / USD 3.50.

Is Parasail cheaper than other providers?

It depends on the model. Of 33 models that other providers also price, Parasail is the cheapest standard price for 1, for example Qwen3 Coder Next; it ties the lowest price, without beating it, for 2 more; another provider is cheaper for 30; and it is the dearest for 5. Its median rank is 4 of a median 10 providers, on a 3:1 input-to-output blend.

Does Parasail have batch, cached or priority pricing?

Cached input: yes, for 38 of 39 standard prices, at a median 36% of the input price. Other tiers: fast on 1 row (median input 1.5× standard).

How much does a chatbot cost per month on Parasail?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 6.12 on GPT OSS 20B, USD 28.98 on Qwen3-VL 8B (the middle of Parasail's list) and USD 394.20 on Kimi K3. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity