Fireworks API pricing
11 Fireworks models live through one API key and one balance, priced per million tokens.
Every Fireworks model below is callable right now through Rapid Router with one API key. The price next to each model is the provider's list price per million tokens; it is exactly what your balance is debited. Our platform fee is charged once, when you buy credits, so there is nothing added per request.
To use a Fireworks model, point the OpenAI SDK (or any OpenAI-compatible client) at https://rapidrouter.ai/api/v1, set the model string to the id shown in grey, and send the same request you send today.
DeepSeek V4.1 Flash model for reasoning and agentic coding
Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality
Flagship GLM model for long-horizon coding, agents, and complex project delivery
Native multimodal GLM model for efficient coding and long-horizon agent tasks
Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
Flagship GLM model for long-horizon coding, agents, and complex project delivery
Kimi K3 with thinking disabled for low-latency tool calling, vision, and JSON work