Fireworks AI

Inference host · 9 models · 18 priced routes · fireworks.ai

Models on Fireworks AI

About Fireworks AI

Fireworks AI is an American artificial intelligence infrastructure company headquartered in San Mateo, California.

Batch: Process large volumes of requests asynchronously at 50% off Serverless per-token prices (docs.fireworks.ai batch-inference)

Caching: Batch jobs automatically use prompt caching for additional 50% cost savings on cached tokens

Across GlyphCompany profile awards Funding rounds 68 incidents in 90 days 8 leaders Paid biweekly, Friday

Model	In / out per 1M	Vs headline
Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.	$0.05 / $0.2+79% vs headline	+79%	NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
DeepSeek V4 Flash 0423 DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.	$0.105 / $0.21+17% vs headline	+17%	DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
GLM 5.3 Flash GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.15 / $0.5+389% vs headline	+389%	GLM-5.3-Flash is a native multimodal model from Z.ai.
DeepSeek V4.1 Flash spot · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.21 / $0.84+238% vs headline	+238%	spot · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
DeepSeek V4.1 Flash 1017 spot · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.	$0.21 / $0.84+40% vs headline	+40%	spot · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
DeepSeek V4.1 Flash DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.3 / $1.2+383% vs headline	+383%	DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.	$0.3 / $1.2+100% vs headline	+100%	DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
DeepSeek V4.1 Flash us · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.45 / $1.8+624% vs headline	+624%	us · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
DeepSeek V4.1 Flash 1017 us · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.	$0.45 / $1.8+200% vs headline	+200%	us · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
GLM 5.3 spot · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$0.98 / $3.08+211% vs headline	+211%	spot · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Muse Spark Open Muse Spark Open is a coding-optimized open-weight model.	$1.25 / $4.25Same vs headline	Same	Muse Spark Open is a coding-optimized open-weight model.
Muse Spark Open us · Muse Spark Open is a coding-optimized open-weight model.	$1.25 / $4.25Same vs headline	Same	us · Muse Spark Open is a coding-optimized open-weight model.
GLM 5.3 GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$1.4 / $4.4+344% vs headline	+344%	GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
GLM 5.3 fast · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$2.1 / $6.6+566% vs headline	+566%	fast · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Kimi K3.1 Pro Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.	$2 / $10+76% vs headline	+76%	Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.
Kimi K3 Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$3 / $15Same vs headline	Same	Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3 us · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$4.5 / $22.5+50% vs headline	+50%	us · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3 fast · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$4.5 / $22.5+50% vs headline	+50%	fast · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.