---
id: "fireworks-ai"
gateways: ["hf"]
models: 20
endpoints: 20
tokens_week: 0
token_share: "0.0%"
rank: 111
cheapest_on: "1 of 10 shared models"
cheaper_than: "50% of offers at the median"
latency_p50_ms: 668
tokens_per_second: 67
---
# fireworks-ai

`deepseek-ai/DeepSeek-V4.1-Flash`, `deepseek-ai/DeepSeek-V4-Flash-0731`, `deepseek-ai/DeepSeek-V4-Flash-Vision-Exp`, `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Pro-0813`, `meta-models/Muse-Glimmer-30B`, `MiniMaxAI/MiniMax-M2.7`, `MiniMaxAI/MiniMax-M3`, `moonshotai/Kimi-K2.6`, `moonshotai/Kimi-K2.7-Code`, `moonshotai/Kimi-K3`, `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16`, `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `Qwen/Qwen3.8-2.4T-A95B`, `thinkingmachines/Inkling`, `zai-org/GLM-5.2`, `zai-org/GLM-5.3`, `zai-org/GLM-5.3-Flash`