Fireworks AI API pricing

Model Aggregator

Fireworks AI is a high-performance serverless inference platform for open and open-weight frontier models (DeepSeek, GLM, Qwen, Kimi, MiniMax, GPT-OSS), offering Standard and Priority throughput tiers with cached-input discounts.

Compare the published API prices listed for Fireworks AI. Open a model for its available pricing tiers, source and conditions, or use the cost planner to estimate your own workload.

Models

Prompt Caching

✓

Batch Discount

—

Tool Calling

—

Visit Website →View Official Pricing →

Model36

					Modality
DeepSeek V4 FlashDeepSeek	$0.14	$0.28	$0.028	—	text
DeepSeek V4 Flash (0731)DeepSeek	$0.22	$0.66	$0.007	—	text
DeepSeek V4 Flash Vision ExpDeepSeek	$0.22	$0.66	$0.007	—	text
DeepSeek V4 ProDeepSeek	$1.74	$3.48	$0.145	—	text
DeepSeek V4 Pro (0813)DeepSeek	$1.32	$3.96	$0.044	—	text
DeepSeek V4.1 FlashDeepSeek	$0.3	$1.2	$0.006	—	text
DeepSeek V4.1 Flash (US)DeepSeek	$0.45	$1.8	$0.009	—	text
DeepSeek V4.1 Flash 1017DeepSeek	$0.3	$1.2	$0.006	—	text
Ember-1	$3	$15	$0.3	—	text
GLM 5.1GLM	$1.4	$4.4	$0.26	—	text
GLM 5.1 FastGLM	$2.8	$8.8	$0.52	—	text
GLM 5.2GLM	$1.4	$4.4	$0.14	—	text
GLM 5.2 FastGLM	$2.1	$6.6	$0.21	—	text
GLM 5.2 Fast USGLM	$2.1	$6.6	$0.21	—	text
GLM 5.3GLM	$1.4	$4.4	$0.26	—	text
GLM 5.3 (US)GLM	$2.1	$6.6	$0.39	—	text
GLM 5.3 FastGLM	$2.1	$6.6	$0.39	—	text
GLM 5.3 FlashGLM	$0.15	$0.5	$0.03	—	text
GLM 5.3 Flash (US)GLM	$0.225	$0.75	$0.045	—	text
Kimi K2.6Kimi	$0.95	$4	$0.16	—	text
Kimi K2.6 FastKimi	$2	$8	$0.3	—	text
Kimi K2.7 CodeKimi	$0.95	$4	$0.19	—	text
Kimi K2.7 Code FastKimi	$1.9	$8	$0.38	—	text
Kimi K3Kimi	$3	$15	$0.3	—	text
Kimi K3 (US)Kimi	$4.5	$22.5	$0.45	—	text
Kimi K3 FastKimi	$4.5	$22.5	$0.45	—	text
MiniMax M2.7MiniMax	$0.3	$1.2	$0.06	—	text
MiniMax M3MiniMax	$0.3	$1.2	$0.06	—	text
Muse Glimmer 30B	$0.35	$1.5	$0.04	—	text
Muse Spark Open	$1.25	$4.25	$0.15	—	text
NVIDIA Nemotron 3 Ultra (Preview)Nemotron	$0.6	$2.4	$0.12	—	text
NVIDIA Nemotron 3.5 Lightning 30B A3BNemotron	$0.05	$0.2	$0.01	—	text
OpenAI GPT OSS 120BGPT-OSS	$0.15	$0.6	$0.015	—	text
OpenAI GPT OSS 20BGPT-OSS	$0.07	$0.3	$0.035	—	text
Qwen 3.7 PlusQwen	$0.4	$1.6	$0.08	—	text
Qwen 3.8 MaxQwen	$2	$6	$0.25	—	text

Fireworks AI API cost examples

1,000 requests, each using 1,000 input tokens and 200 billed text output tokens: 1M input and 200K output tokens in total.

Standard text token prices and estimated workload cost in USD
Model	Input / 1M tokens	Output / 1M tokens	Estimated cost	Pricing conditions
NVIDIA Nemotron 3.5 Lightning 30B A3BFireworks AI	$0.05	$0.2	$0.09	Region not specifiedView official pricing
GLM 5.3 FlashFireworks AI	$0.15	$0.5	$0.25	Region not specifiedView official pricing
OpenAI GPT OSS 120BFireworks AI	$0.15	$0.6	$0.27	Region not specifiedView official pricing
GLM 5.3 Flash (US)Fireworks AI	$0.225	$0.75	$0.375	Region not specifiedView official pricing
DeepSeek V4.1 FlashFireworks AI	$0.3	$1.2	$0.54	Region not specifiedView official pricingVerified Sep 23, 2026
DeepSeek V4.1 Flash 1017Fireworks AI	$0.3	$1.2	$0.54	Region not specifiedView official pricing

Estimates in USD use standard processing, uncached input and the displayed base input tier. Regional rates, longer prompts, thinking tokens and other billable usage can change the final cost. Models can differ in capabilities.

Calculate costs for your workload →