FriendliAI · Pricing Plans

Friendliai Plans Pricing

Friendliai Plans Pricing is the pricing profile for FriendliAI on the APIs.io network — every figure transcribed verbatim from the provider’s own pricing page on 2026-09-20.

It defines 15 plans, including GLM-5.3 (Model API) — $1.26 $1.4 Input · $0.234 $0.26 Cached Input · $3.96 $4.4 Output; GLM-5.3-Flash — $0.15 Input · $0.03 Cached Input · $0.5 Output; GLM-5.2 — $1.4 Input · $0.26 Cached Input · $4.4 Output, and 12 more.

The page prices API or platform usage directly, priced per call; the service is delivered as managed plus licensed.

Tagged areas include Company, Infrastructure, Artificial Intelligence, Machine Learning, and LLM.

15 Plans Prices the API Basis: per call Delivered: managed + licensed
Transcribed from the provider's pricing page on 2026-09-20 — friendli.ai/pricing.
View Source
CompanyInfrastructureArtificial IntelligenceMachine LearningLLMInferenceGenerative AIGPUOpenAI-Compatible

Compare with the market: Artificial Intelligence pricing

Plans

GLM-5.3 (Model API) per-use
$1.26 $1.4 Input · $0.234 $0.26 Cached Input · $3.96 $4.4 Output per per 1M tokens
GLM-5.3-Flash per-use
$0.15 Input · $0.03 Cached Input · $0.5 Output per per 1M tokens
GLM-5.2 per-use
$1.4 Input · $0.26 Cached Input · $4.4 Output per per 1M tokens
GLM-5.1 per-use
$1.4 Input · $0.26 Cached Input · $4.4 Output per per 1M tokens
gemma-4-31B-it per-use
$0.14 Input · $0.4 Output per per 1M tokens
DeepSeek-V3.2 per-use
$0.5 Input · $0.25 Cached Input · $1.5 Output per per 1M tokens
MiniMax-M2.5 per-use
$0.3 Input · $0.06 Cached Input · $1.2 Output per per 1M tokens
whisper-large-v3 (STT) per-use
$0.0015 per per audio minute
Dedicated Endpoint A100 80GB per-use
$ 2.9 per per hour (billed per second), through Sep 30; $ 4.0 effective Oct 1
Dedicated Endpoint H100 80GB per-use
$ 3.9 per per hour (billed per second), through Sep 30; $ 5.0 effective Oct 1
Dedicated Endpoint H200 141GB per-use
$ 4.5 per per hour (billed per second), through Sep 30; $ 7.0 effective Oct 1
Dedicated Endpoint B200 180GB per-use
$ 8.9 per per hour (billed per second), through Sep 30; $ 9.0 effective Oct 1
Dedicated Endpoint B300 288GB per-use
$ 12.0 per per hour (billed per second)
BYOG none
Contact us
Enterprise none
Contact Sales
Includes: Custom Model APIs rate limits, priority GPU access, reserved capacity, VPC/on-prem deployment, dedicated support

Sources

Work with this as data

Every plan here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for plans

4 MCP tools reach this
  • find_plansBrowse and filter every plan in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This plan 
curl "https://apis.io/api/v1/plans/friendliai-plans-pricing"
All plans 
curl "https://apis.io/api/v1/plans?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.