BroadRouter

Sail Research API pricing

Updated

Sail Research lists standard per-token prices for 8 models. The cheapest is DeepSeek V4 Flash 0731 at USD 0.09 input and USD 0.18 output per 1M tokens; the dearest is Kimi K3.1 Pro at USD 1.50 / USD 10. It publishes cached-input prices for all of them, plus flex / spot prices (no batch or priority). Checked 2026-11-16.

Sail Research hosts models it does not train. By maker: DeepSeek 3, Google 2, Z.ai 2, Moonshot AI 1, Qwen 1. 17 prices, each read from Sail Research's own pricing page, checked 2026-11-16. BroadRouter is BroadNet's own site and does not sell Sail Research's services.

Models with a standard price
8
Median input / output
USD 0.35 / USD 1.30
Cached-input prices
8 of 8
Cheapest host for
2 of 8 shared models

Which models is Sail Research the cheapest provider for?

Of the 8 models that Sail Research and at least one other provider both price at the standard tier, Sail Research has the lowest price for 2, ranked on a blend of 3 input tokens to 1 output token. It is the dearest for 1.

Models where Sail Research is the cheapest provider
ModelSail Research input / outputNext cheapestSaving on 3:1 blendProviders
DeepSeek V4.1 Flash 1017USD 0.09 / USD 0.30DeepInfra USD 0.098 / USD 0.2943%23
Kimi K3.1 ProUSD 1.50 / USD 10DeepInfra USD 1.90 / USD 9.505%20

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

Sail Research on the most widely hosted models
ModelSail ResearchRankCheapest
GLM 5.3USD 0.98 / USD 3.086 of 31DeepInfra USD 0.5625 / USD 2.50
GLM 5.3 FlashUSD 0.11 / USD 0.352 of 29GMI Cloud USD 0.075 / USD 0.25
DeepSeek V4.1 Flash 1017USD 0.09 / USD 0.301 of 23Sail Research (this page)
Kimi K3.1 ProUSD 1.50 / USD 101 of 20Sail Research (this page)
DeepSeek V4 Pro 0813USD 0.92 / USD 2.772 of 17Chutes USD 0.85 / USD 2.65
DeepSeek V4 Flash 0731USD 0.09 / USD 0.183 of 17DeepInfra USD 0.06 / USD 0.18

Which model makers does Sail Research sell?

Sail Research prices models from 4 makers. DeepSeek leads with 3 models. Standard prices, USD per 1M input / output tokens.

Sail Research models by maker
MakerModelsCheapest modelMedian input / output
DeepSeek3DeepSeek V4 Flash 0731 USD 0.09 / USD 0.18USD 0.09 / USD 0.30
Google2Gemma 4 31B USD 0.40 / USD 0.60USD 0.35 / USD 1.30
Z.ai2GLM 5.3 Flash USD 0.11 / USD 0.35USD 0.545 / USD 1.715
Moonshot AI1Kimi K3.1 Pro USD 1.50 / USD 10—

Sail Research price list

USD per 1M tokens: 17 prices for 9 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-16 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 Sail Research is cheaper. Of 5 hosted model prices with a maker price to compare, 5 are below the maker's and 0 above.

Sail Research API prices by model
ModelTierInputCachedOutputContextvs makerSource
DeepSeek V4 Flash 0731standard
flex / spot
USD 0.09
USD 0.05
USD 0.02
USD 0.01
USD 0.18
USD 0.09
not stated—source
DeepSeek V4 Pro 0813standard
flex / spot
USD 0.92
USD 0.46
USD 0.04
USD 0.02
USD 2.77
USD 1.39
not stated−30%source
DeepSeek V4.1 Flash 1017standard
flex / spot
USD 0.09
USD 0.05
USD 0.006
USD 0.004
USD 0.30
USD 0.15
not stated−73%source
Gemma 4 12B ITstandard
flex / spot
USD 0.30
USD 0.05
USD 0.15
USD 0.02
USD 2
USD 1
not stated—source
Gemma 4 31Bstandard
flex / spot
USD 0.40
USD 0.06
USD 0.20
USD 0.02
USD 0.60
USD 0.30
not stated—source
GLM 5.3standard
flex / spot
USD 0.98
USD 0.40
USD 0.18
USD 0.08
USD 3.08
USD 1.80
not stated−30%source
GLM 5.3 Flashstandard
flex / spot
USD 0.11
USD 0.05
USD 0.02
USD 0.01
USD 0.35
USD 0.18
not stated−28%source
Kimi K3.1 Prostandard
flex / spot
USD 1.50
USD 0.70
USD 0.20
USD 0.10
USD 10
USD 6
not stated−9%source
Qwen3.6 35B A3Bflex / spotUSD 0.05USD 0.02USD 0.40not stated—source
  • Cached "—" means Sail Research's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": Sail Research'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 Sail Research publish?

  • flex / spot (9 rows). Across 8 models with both prices, median flex / spot input is 54% below standard and median output 50% below standard. Sail Research row note: “Flex service tier: first turn may queue up to 1 hour; background requests only.”

Cached input: 8 of 8 standard prices include a cache-read price, a median 18% of the input price. What cached input means.

What we recorded about Sail Research's pricing page: Prices from the "Core models" and "Flex-only models" tables on docs.sailresearch.com/pricing (Input, Cached, Output, USD per 1M tokens; "All inputs include a guaranteed cache write with a 1-hour TTL"). Default (ASAP) is the standard row. Excluded: Gemma 4 31B IT (NVFP4), a second, cheaper quantized endpoint of Gemma 4 31B IT (0.14 in, 0.07 cached, 0.40 out at Default), so one standard row per model is kept. No context length is shown on the pricing page.

Is Sail Research cheaper than the model makers' own APIs?

Mostly yes. Of 5 standard prices for models whose maker sells its own API, 5 are below the maker's price, 0 above and 0 the same, on the 3:1 blend. The median difference is 30% below the maker. The biggest saving is DeepSeek V4.1 Flash 1017, 73% below DeepSeek.

BroadNet Inference and Sail Research

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 1 model that Sail Research prices: GLM 5.3 at USD 0.78 / USD 3.46 against Sail Research's USD 0.98 / USD 3.08 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on Sail Research

Questions

How much does the Sail Research API cost per token?

Sail Research's standard prices run from USD 0.09 input and USD 0.18 output per 1M tokens (DeepSeek V4 Flash 0731) to USD 1.50 / USD 10 (Kimi K3.1 Pro). The median across 8 standard prices is USD 0.35 input and USD 1.30 output per 1M, which is USD 0.00000035 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Sail Research?

DeepSeek V4 Flash 0731, at USD 0.09 input and USD 0.18 output per 1M tokens (USD 0.1125 on a 3:1 input-to-output blend). The cheapest from other makers: Gemma 4 31B (Google) at USD 0.40 / USD 0.60; GLM 5.3 Flash (Z.ai) at USD 0.11 / USD 0.35; Kimi K3.1 Pro (Moonshot AI) at USD 1.50 / USD 10.

Is Sail Research cheaper than other providers?

It depends on the model. Of 8 models that other providers also price, Sail Research is the cheapest standard price for 2, for example DeepSeek V4.1 Flash 1017 and Kimi K3.1 Pro; another provider is cheaper for 6; and it is the dearest for 1. Its median rank is 2 of a median 18.5 providers, on a 3:1 input-to-output blend.

Does Sail Research have batch, cached or priority pricing?

Cached input: yes, for 8 of 8 standard prices, at a median 18% of the input price. Other tiers: flex / spot on 9 rows (median input 54% below standard).

How much does a chatbot cost per month on Sail Research?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 7.56 on DeepSeek V4 Flash 0731, USD 36.00 on Gemma 4 31B (the middle of Sail Research's list) and USD 244.80 on Kimi K3.1 Pro. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity