FriendliAI API pricing
Updated
FriendliAI lists standard per-token prices for 5 models. The cheapest is Gemma 4 31B at USD 0.14 input and USD 0.40 output per 1M tokens; the dearest is GLM 5.2 at USD 1.40 / USD 4.40. It publishes cached-input prices for 4 of them, and lists no per-model batch, flex or priority prices on the pages we read. Checked 2026-11-15.
- Models with a standard price
- 5
- Median input / output
- USD 1.26 / USD 3.96
- Cached-input prices
- 4 of 5
- Cheapest host for
- 0 of 5 shared models
Which models is FriendliAI the cheapest provider for?
None. Every one of the 5 models that FriendliAI shares with other providers is cheaper elsewhere at the standard tier. The closest is GLM 5.3 Flash, where FriendliAI ranks 3 of 20.
How does FriendliAI price the most widely hosted models?
The 5 models FriendliAI sells that the most other providers also sell, with FriendliAI's rank among them on the 3:1 blend.
| Model | FriendliAI | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 1.26 / USD 3.96 | 5 of 24 | DeepInfra USD 0.5625 / USD 2.50 |
| GLM 5.3 Flash | USD 0.15 / USD 0.50 | 3 of 20 | GMI Cloud USD 0.075 / USD 0.25 |
| GLM 5.2 | USD 1.40 / USD 4.40 | 5 of 19 | DeepInfra USD 0.5625 / USD 1.80 |
| Gemma 4 31B | USD 0.14 / USD 0.40 | 4 of 12 | CoreWeave Forge USD 0.10 / USD 0.34 |
| GLM 5.1 | USD 1.40 / USD 4.40 | 5 of 12 | Chutes USD 0.90 / USD 2.90 |
Which model makers does FriendliAI sell?
FriendliAI prices models from 2 makers. Z.ai leads with 4 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| Z.ai | 4 | GLM 5.3 Flash USD 0.15 / USD 0.50 | USD 1.33 / USD 4.18 |
| 1 | Gemma 4 31B USD 0.14 / USD 0.40 | — |
FriendliAI price list
USD per 1M tokens: 5 prices for 5 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 FriendliAI is cheaper. Of 4 hosted model prices with a maker price to compare, 1 is below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| Gemma 4 31B | standard | USD 0.14 | — | USD 0.40 | 262,144 | — | source |
| GLM 5.1 | standard | USD 1.40 | USD 0.26 | USD 4.40 | 203,000 | same | source |
| GLM 5.2 | standard | USD 1.40 | USD 0.26 | USD 4.40 | 1,048,576 | same | source |
| GLM 5.3promo | standard | USD 1.26 | USD 0.234 | USD 3.96 | 1,048,576 | −10% | source |
| GLM 5.3 Flash | standard | USD 0.15 | USD 0.03 | USD 0.50 | 1,048,576 | same | source |
- Cached "—" means FriendliAI's page shows no cache price for that row; budget cached tokens at the input price.
- Promo: FriendliAI's page describes 1 price as promotional or discounted; they can end without notice. Each model page has the list price where the source gives one.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does FriendliAI publish?
Standard prices only: FriendliAI publishes no per-model batch, flex, priority or fast price on the pages we read.
Cached input: 4 of 5 standard prices include a cache-read price, a median 19% of the input price. What cached input means.
What we recorded about FriendliAI's pricing page: Friendli Model APIs (serverless) per-token prices from friendli.ai/pricing and each model page (same values on friendli.ai/docs/guides/model-apis/pricing). Context from the model pages (1M read as 1048576). Dedicated Endpoints are billed per GPU-hour and are not listed. Audio models excluded.
Is FriendliAI cheaper than the model makers' own APIs?
Mostly it charges the same as the maker. Of 4 standard prices for models whose maker sells its own API, 1 is below the maker's price, 0 above and 3 the same, on the 3:1 blend. The median difference is zero. The biggest saving is GLM 5.3, 10% below Z.ai.
BroadNet Inference and FriendliAI
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 1 model that FriendliAI prices: GLM 5.3 at USD 0.78 / USD 3.46 against FriendliAI's USD 1.26 / USD 3.96 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on FriendliAI
- FriendliAI's own pricing page (the source; checked 2026-11-15)
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Questions
How much does the FriendliAI API cost per token?
FriendliAI's standard prices run from USD 0.14 input and USD 0.40 output per 1M tokens (Gemma 4 31B) to USD 1.40 / USD 4.40 (GLM 5.2). The median across 5 standard prices is USD 1.26 input and USD 3.96 output per 1M, which is USD 0.00000126 per input token. Input, cached input and output are billed separately.
What is the cheapest model on FriendliAI?
Gemma 4 31B, at USD 0.14 input and USD 0.40 output per 1M tokens (USD 0.205 on a 3:1 input-to-output blend). The cheapest from other makers: GLM 5.3 Flash (Z.ai) at USD 0.15 / USD 0.50.
Is FriendliAI cheaper than other providers?
It depends on the model. Of 5 models that other providers also price, FriendliAI is the cheapest standard price for none; another provider is cheaper for 5; and it is the dearest for none. Its median rank is 5 of a median 19 providers, on a 3:1 input-to-output blend.
Does FriendliAI have batch, cached or priority pricing?
Cached input: yes, for 4 of 5 standard prices, at a median 19% 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 FriendliAI?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 16.02 on GLM 5.3 Flash, USD 129.28 on GLM 5.3 (the middle of FriendliAI's list) and USD 143.64 on GLM 5.2. Try your own numbers.