Skip to main content
Source: Fireworks model docs. All model IDs use the prefix fireworks/accounts/fireworks/models/. Only serverless models are listed here — other Fireworks models require a dedicated deployment.

​
All Models

deepseek-v4-flash-0731

Reasoning · Speedfireworks/accounts/fireworks/models/deepseek-v4-flash-0731Official DeepSeek V4 Flash on Fireworks serverless (supersedes the April preview). Fast, cost-efficient MoE with near-Pro reasoning at 1M context.
  • $0.22 / $0.66
  • 1M context
  • Text input

qwen3p8-max

Reasoning · Speedfireworks/accounts/fireworks/models/qwen3p8-maxAlibaba Qwen 3.8 Max on Fireworks serverless: flagship MoE for long-horizon coding and agentic work. Replacement for retired qwen3p7-plus.
  • $2.00 / $6.00
  • 262K context
  • Text input

kimi-k2p6

Reasoning · Speedfireworks/accounts/fireworks/models/kimi-k2p6Moonshot Kimi K2.6 on Fireworks: multimodal MoE for high-quality tool use and long-context workloads.
  • $0.95 / $4.00
  • 262K context
  • Text, Image input

kimi-k2p7-code

Reasoning · Speedfireworks/accounts/fireworks/models/kimi-k2p7-codeMoonshot Kimi K2.7 Code on Fireworks serverless for long-context coding agents with thinking mode.
  • $0.95 / $4.00
  • 262K context
  • Text, Image input
  • Thinking

glm-5p2

Reasoning · Speedfireworks/accounts/fireworks/models/glm-5p2Z.ai GLM-5.2 on Fireworks serverless: 1M-token context, strongest open coding model with prompt caching (cached input $0.14 / 1M).
  • $1.40 / $4.40
  • 1M context
  • Text input

minimax-m3

Reasoning · Speedfireworks/accounts/fireworks/models/minimax-m3MiniMax M3 multimodal MoE on Fireworks serverless for chat, agents, and long-context workloads.
  • $0.30 / $1.20
  • 512K context
  • Text, Image input

gpt-oss-120b

Reasoning · Speedfireworks/accounts/fireworks/models/gpt-oss-120bOpenAI’s open-weight 120B MoE achieving near-parity with o4-mini on reasoning benchmarks. Apache 2.0.
  • $0.15 / $0.60
  • 128K context
  • Text input