---
id: "fireworks"
site: "fireworks.ai"
headquarters: "US"
gateways: ["openrouter", "requesty", "vercel"]
models: 44
endpoints: 91
tokens_week: 188480208002
token_share: "1.2%"
rank: 18
cheapest_on: "15 of 80 shared models"
cheaper_than: "57% of offers at the median"
vs_card: "at the card price at the median over 26 models"
cache_hit: "86.6%"
uptime_1d: 98.3000
latency_p50_ms: 983
tokens_per_second: 102
trains_on_some: false
retains_on_some: false
quantization: "unknown (32), fp4 (6), bf16 (2), fp8 (2)"
---
# Fireworks

`alibaba/qwen3.7-plus`, `alibaba/qwen3.8-2.4t-a95b`, `alibaba/qwen3.8-max`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4.1-flash-1017-ultrafast`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0731`, `deepseek/deepseek-v4-flash-vision-exp`, `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-pro-0813`, `fireworks/ember-1`, `meta/muse-glimmer-30b`, `meta/muse-spark-open`, `minimax/minimax-m2.7`, `minimax/minimax-m3`, `minimax/minimax-m3.1-flash`, `moonshotai/kimi-k2.6`, `moonshotai/kimi-k2.7-code`, `moonshotai/kimi-k2.7-code-highspeed`, `moonshotai/kimi-k3`, `moonshotai/kimi-k3.1-pro`, `moonshotai/kimi-k3-fast`, `moonshot/kimi-k2.6`, `moonshot/kimi-k2.7-code`, `moonshot/kimi-k3`, `moonshot/kimi-k3.1-pro`, `nvidia/nemotron-3.5-lightning`, `nvidia/nemotron-3-ultra-550b-a55b`, `nvidia/nemotron-3-ultra-nvfp4`, `nvidia/nemotron-lightning-3.5-30b-a3b`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `paper-instruments/ultramarine-1-flash`, `qwen/qwen3.8-2.4t-a95b`, `qwen/qwen3-reranker-8b`, `zai/glm-5.1`, `z-ai/glm-5.2`, `zai/glm-5.2`, `zai/glm-5.2-fast`, `z-ai/glm-5.3`, `zai/glm-5.3`, `z-ai/glm-5.3-flash`, `zai/glm-5.3-flash`