Skip to main content

Fireworks AI

Inference host

Fireworks AI runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.

PricingDocs
Visit fireworks.ai
Models10
Cheapest for
1 models
Serves
1 model types
Visits in September 2026622K−12.8%Unique visitors 264K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on Fireworks AI

ModelInputOutputvs officialContext
Kimi K3$3/1MFrom$15/1M
from $8.28 at Kenari
+8%—
GLM-5.3$1.40/1MFrom$4.40/1M
from $1.10 at NanoGPT
±0%—
GLM-5.3-Flash$0.15/1MFrom$0.50/1M
from $0.20 at APIMart
±0%—
Muse Spark Open$1.25/1MFrom$4.25/1M±0%—
GPT OSS 120B$0.15/1MFrom$0.60/1M
from $0.14 at Requesty
+329%—
MiniMax-M3$0.30/1MFrom$1.20/1M
from $0.90 at EmpirioLabs AI
±0%—
Nemotron 3.5 Lightning 30B A3B$0.05/1MFrom$0.20/1M
from $0.16 at Deep Infra
——
Nemotron 3 Ultra 550B A55B$0.60/1MFrom$2.40/1M
from $2.20 at Deep Infra
——
Ember-1Cheapest$3/1MFrom$15/1MOfficial—
Kimi K3 UsOnly here$4.50/1MFrom$22.50/1M——

Fireworks AI at a glance

10 models in total: 10 text. The cheapest is Nemotron 3.5 Lightning 30B A3B at $0.20 /1M. Kimi K3 has the largest context window, 1.05M tokens. The most searched is Kimi K3, with about 658K Google searches a month. The newest is Muse Spark Open, released Oct 15, 2026.

Cheapest

  1. Nemotron 3.5 Lightning 30B A3B$0.20/1M
  2. GLM-5.3-Flash$0.50/1M
  3. GPT OSS 120B$0.60/1M
  4. MiniMax-M3$1.20/1M
  5. Nemotron 3 Ultra 550B A55B$2.40/1M

Largest context

  1. Kimi K31.05M
  2. GLM-5.31.05M
  3. GLM-5.3-Flash1.05M
  4. Muse Spark Open1.05M
  5. Ember-11.05M

Most searched

  1. Kimi K3658K
  2. GLM-5.3276K
  3. GLM-5.3-Flash121K
  4. Muse Spark Open74K
  5. GPT OSS 120B35K

Newest

  1. Muse Spark OpenOct 15, 2026
  2. Ember-1Sep 23, 2026
  3. GLM-5.3Aug 25, 2026
  4. GLM-5.3-FlashAug 25, 2026
  5. Nemotron 3.5 Lightning 30B A3BAug 11, 2026