Fireworks AI
Fireworks AI is an AI model provider.Tokenando tracks 9 Fireworks AI models, with input pricing from $0.100/M and an average blended cost of $1.244/M. Its flagship model is Qwen2.5-72B (fw).
Serverless open-model inference focused on low latency. Function calling, JSON mode and LoRA hosting.
MODELS TRACKED
9
3 categories
FLAGSHIP
Qwen2.5-72B (fw)
Live API
MIN INPUT
$0.100/M
cheapest model in family
AVG BLENDED
$1.244/M
across 9 priced models
MAX CONTEXT
131,000
largest window in family
Frontier
1 model
Reasoning
1 model
Efficient
7 models
Mixtral 8x7B (fw)profile
Live API · 32,000 ctx
in $0.200/Mout $0.200/M
MoE serverless · manual-seed
Qwen2.5-72B (fw)profile
Live API · 32,000 ctx
in $0.900/Mout $0.900/M
Qwen serverless · manual-seed
Llama 3.1 8B (fw)profile
Live API · 131,000 ctx
in $0.100/Mout $0.100/M
Cheapest 8B · manual-seed
Yi-34B (fw)profile
Live API · 4,000 ctx
in $0.900/Mout $0.900/M
Yi on Fireworks · manual-seed
Phind-CodeLlama-34B (fw)profile
Live API · 16,000 ctx
in $0.800/Mout $0.800/M
Code specialist · manual-seed
Inception: Mercury 2
text->text · 128,000 ctx
in $0.250/Mout $0.750/M
tokenizer: Other · cron:openrouter
Mercury 2
text->text · 128,000 ctx
in $0.250/Mout $0.750/M
Frequently Asked Questions
How many models does Fireworks AI offer?
Tokenando tracks 9 Fireworks AI models.
How much do Fireworks AI models cost?
Fireworks AI model input pricing starts at $0.100 per million tokens, with an average blended cost of $1.244 per million across the 9 priced models we track.
What is Fireworks AI's flagship model?
Fireworks AI's flagship model is Qwen2.5-72B (fw). It is the highest-tier Fireworks AI model we track, with input pricing of $0.900 per million tokens.
What model categories does Fireworks AI cover?
Fireworks AI covers 3 categories: frontier, reasoning and efficient.