The AI arena is free today

Open Superagent
API Provider4 active models3 organizations

FriendliAI: API pricing, speed & models

FriendliAI hosts 4 active AI models, with input pricing from $0.14 per 1M tokens, with median throughput of 277 characters/sec, with 100% success rate over 7 days. Compare FriendliAI's API speed, pricing, and reliability against other inference providers.

Median throughput277 c/s
Success rate (7d)100%
From$0.14 /M tok

Catalog

Zhipu AI3Google2
Type
Price
5 models
Model
GLM-5.2cache pricing
GLM-5.1cache pricing
At a glance

FriendliAIpricing, performance & catalog

The citable facts about FriendliAI's 4 models — sourced from provider APIs and refreshed continuously.

Lowest price
Gemma 4 31B at $0.140 per 1M input tokens
Highest median throughput
Gemma 4 31B at 277 chars/s
Largest context
GLM-5.2 at 1.0M tokens
Catalog
4 active models from 3 organizations

Fastest median throughput

  1. 1Gemma 4 31B277 c/s

FAQ

Common questions about FriendliAI.

What is FriendliAI?

FriendliAI is an API provider that hosts large language models. Active models: 4; From (input): $0.14 / 1M tok; Median throughput: 277 c/s; Success rate (7d): 100%.

How many models does FriendliAI offer?

FriendliAI currently serves 4 active models out of 5 historical offerings on LLM Stats.

What is FriendliAI's API pricing?

FriendliAI input pricing starts from $0.14 per 1M tokens, with the most expensive offering at $1.4 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

How fast is FriendliAI?

FriendliAI delivers a median throughput of 277 characters per second across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is FriendliAI reliable?

FriendliAI has a 100% success rate across 4 API calls in the last 7 days, with a 0% error rate.

Does FriendliAI support function calling?

Yes. 5 of 4 models on FriendliAI support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does FriendliAI support JSON mode and structured output?

Yes. 5 of 4 models on FriendliAI support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Does FriendliAI support multimodal models?

Yes. FriendliAI's catalog includes 1 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Whose models does FriendliAI host?

FriendliAI hosts models from Google, Zhipu AI, and LG AI Research. See the Models tab for the full catalog grouped by creator.

How do I start using FriendliAI?

Sign up at https://friendli.ai/ to get an API key, then call FriendliAI's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at FriendliAI's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.