FriendliAI models and pricing
We track 5 models on FriendliAI from 2 labs. The cheapest paid model is Gemma 4 31B IT, at $0.14 per million input tokens and $0.40 per million output tokens. Input prices range from $0.14 to $1.40 and output prices from $0.40 to $4.40 per million tokens. The largest context window is 1M tokens (GLM-5.3-Flash, GLM-5.3 and GLM-5.2). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on FriendliAI
- Gemma 4 31B IT$0.14 / $0.40
- GLM-5.3-Flash$0.15 / $0.50
- GLM-5.3$1.26 / $3.96
- GLM-5.1$1.40 / $4.40
- GLM-5.2$1.40 / $4.40
Input / output per million tokens, paid models, by combined price.
Newest models on FriendliAI
- GLM-5.3-Flash26 Aug 2026
- GLM-5.314 Aug 2026
- GLM-5.213 Jun 2026
- GLM-5.17 Apr 2026
- Gemma 4 31B IT2 Apr 2026
By the lab's release date.
All FriendliAI models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| GLM-5.3-Flash zai-org/GLM-5.3-Flash | Zhipu AI (Z.ai) | $0.15 | $0.50 | 1M | models.dev |
| GLM-5.3 zai-org/GLM-5.3 | Zhipu AI (Z.ai) | $1.26 | $3.96 | 1M | models.dev |
| GLM-5.2 zai-org/GLM-5.2 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| GLM-5.1 zai-org/GLM-5.1 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 203K | models.dev |
| Gemma 4 31B IT google/gemma-4-31B-it | Google DeepMind | $0.14 | $0.40 | 262K | models.dev |
Frequently asked questions
How much does FriendliAI cost per million tokens?
Prices on FriendliAI depend on the model. Across the 5 models we track, input costs $0.14 to $1.40 per million tokens and output costs $0.40 to $4.40 per million tokens. Prices last verified 18 Nov 2026.
What is the cheapest model on FriendliAI?
Gemma 4 31B IT from Google DeepMind is the cheapest paid model we track on FriendliAI, at $0.14 per million input tokens and $0.40 per million output tokens. Next are GLM-5.3-Flash ($0.15 / $0.50) and GLM-5.3 ($1.26 / $3.96). Prices last verified 18 Nov 2026.
How many models does FriendliAI offer?
We currently track 5 active models on FriendliAI from 2 labs, led by Zhipu AI (Z.ai) (4) and Google DeepMind (1).
Which model on FriendliAI has the largest context window?
GLM-5.3-Flash, GLM-5.3 and GLM-5.2 share the largest context window we track on FriendliAI: 1,048,576 tokens (1M).