BroadRouter

Modal API pricing

Updated

Modal lists standard prices for 10 models. The cheapest is DeepSeek V4.1 Flash 1017 at USD 0.25 input and USD 1 output per 1M tokens; the dearest is Kimi K3 at USD 3 / USD 15. It publishes cached-input prices for all of them, and lists no per-model batch, flex or priority prices on the pages we read.

Modal hosts models it does not train. By maker: DeepSeek 2, Moonshot AI 2, Thinking Machines 2, Z.ai 2, Meta 1, Qwen 1. 10 prices, each read from Modal's own pricing page, checked 2026-11-16. BroadRouter is BroadNet's own site and does not sell Modal's services.

Models with a standard price
10
Median input / output
USD 1.225 / USD 4.325
Cached-input prices
10 of 10
Cheapest host for
0 of 10 shared models

Which models is Modal the cheapest provider for?

None outright. Of the 10 models that Modal shares with other providers, 9 are cheaper elsewhere at the standard tier, and Modal ties the lowest price for the other 1, where another provider charges the same. It is the dearest provider for 5.

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

Modal on the most widely hosted models
ModelModalRankCheapest
GLM 5.3USD 1.40 / USD 4.4010 of 31DeepInfra USD 0.5625 / USD 2.50
GLM 5.3 FlashUSD 0.45 / USD 1.5029 of 29GMI Cloud USD 0.075 / USD 0.25
Kimi K3USD 3 / USD 156 of 23Chutes USD 1.85 / USD 9.50
DeepSeek V4.1 Flash 1017USD 0.25 / USD 18 of 23Sail Research USD 0.09 / USD 0.30
DeepSeek V4.1 FlashUSD 0.30 / USD 1.2010 of 23Relace USD 0.07 / USD 0.50
Kimi K3.1 ProUSD 2 / USD 104 of 20Sail Research USD 1.50 / USD 10

Which model makers does Modal sell?

Modal prices models from 6 makers. DeepSeek leads with 2 models. Standard prices, USD per 1M input / output tokens.

Modal models by maker
MakerModelsCheapest modelMedian input / output
DeepSeek2DeepSeek V4.1 Flash 1017 USD 0.25 / USD 1USD 0.275 / USD 1.10
Moonshot AI2Kimi K3.1 Pro USD 2 / USD 10USD 2.50 / USD 12.50
Thinking Machines2Inkling 2 Small USD 0.30 / USD 1USD 0.75 / USD 3
Z.ai2GLM 5.3 Flash USD 0.45 / USD 1.50USD 0.925 / USD 2.95
Meta1Muse Spark Open USD 1.25 / USD 4.25—
Qwen1Qwen3.8 Max USD 2 / USD 6—

Modal price list

USD per 1M tokens: 10 prices for 10 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 Modal is cheaper. Of 7 hosted model prices with a maker price to compare, 1 is below the maker's and 1 above.

Modal API prices by model
ModelTierInputCachedOutputContextvs makerSource
DeepSeek V4.1 FlashstandardUSD 0.30USD 0.03USD 1.20not statedsamesource
DeepSeek V4.1 Flash 1017standardUSD 0.25USD 0.005USD 1not stated−17%source
GLM 5.3standardUSD 1.40USD 0.26USD 4.40not statedsamesource
GLM 5.3 FlashstandardUSD 0.45USD 0.09USD 1.50not stated+200%source
Inkling 2 SmallstandardUSD 0.30USD 0.03USD 1not stated—source
Inkling NVFP4standardUSD 1.20USD 0.27USD 5not stated—source
Kimi K3standardUSD 3USD 0.30USD 15not statedsamesource
Kimi K3.1 ProstandardUSD 2USD 0.20USD 10not statedsamesource
Muse Spark OpenstandardUSD 1.25USD 0.15USD 4.25not stated—source
Qwen3.8 MaxstandardUSD 2USD 0.25USD 6not statedsamesource
  • Cached "—" means Modal's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": Modal'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 Modal publish?

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

Cached input: 10 of 10 standard prices include a cache-read price, a median 11% of the input price. What cached input means.

What we recorded about Modal's pricing page: Prices from the "Model APIs / 1M tokens" table on modal.com/pricing (Prompt, Cached prompt and Completion per 1M tokens, USD). GPU, CPU, sandbox and plan prices on the same page are not per-token and are excluded. Excluded: GLM 5.3 Flash NVFP4 (a second, cheaper quantized endpoint of GLM 5.3 Flash: 0.15 in, 0.03 cached, 0.50 out; one standard row per model is kept) and Qwen3.8-Max VL (no matching model page). No context length or model IDs are shown in the table.

Is Modal cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 7 standard prices for models whose maker sells its own API, 1 is below the maker's price, 1 above and 5 the same, on the 3:1 blend. The median difference is zero. The biggest saving is DeepSeek V4.1 Flash 1017, 17% below DeepSeek. The biggest markup is GLM 5.3 Flash, 200% above Z.ai.

BroadNet Inference and Modal

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that Modal prices: DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Modal'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 Modal'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 Modal

Questions

How much does the Modal API cost per token?

Modal's standard prices run from USD 0.25 input and USD 1 output per 1M tokens (DeepSeek V4.1 Flash 1017) to USD 3 / USD 15 (Kimi K3). The median across 10 standard prices is USD 1.225 input and USD 4.325 output per 1M, which is USD 0.000001225 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Modal?

DeepSeek V4.1 Flash 1017, at USD 0.25 input and USD 1 output per 1M tokens (USD 0.4375 on a 3:1 input-to-output blend). The cheapest from other makers: Kimi K3.1 Pro (Moonshot AI) at USD 2 / USD 10; Inkling 2 Small (Thinking Machines) at USD 0.30 / USD 1; GLM 5.3 Flash (Z.ai) at USD 0.45 / USD 1.50.

Is Modal cheaper than other providers?

It depends on the model. Of 10 models that other providers also price, Modal is the cheapest standard price for none; it ties the lowest price, without beating it, for 1; another provider is cheaper for 9; and it is the dearest for 5. Its median rank is 5 of a median 21.5 providers, on a 3:1 input-to-output blend.

Does Modal have batch, cached or priority pricing?

Cached input: yes, for 10 of 10 standard prices, at a median 11% 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 Modal?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 27.27 on DeepSeek V4.1 Flash 1017, USD 129.60 on Muse Spark Open (the middle of Modal's list) and USD 394.20 on Kimi K3. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity