FW-DeepSeek-V4-Flash-0731
FireworksModels available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Non-Microsoft Product. The following terms apply to a Customer's use of Fireworks on Foundry: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, Customer Data will be sent outside of Microsoft systems, Customer Data will not be processed pursuant to any Foundry data residency documentation, and different compliance and data handling rules will apply. See Trust Center - Fireworks AI for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization's compliance requirements.
About this model
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version with substantially enhanced agentic capabilities. It is a 304B-parameter Mixture-of-Experts language model with a one-million-token context window and the same model structure as DeepSeek-V4-Flash-DSpark, including an attached speculative decoding module. The model supports function calling and three reasoning-effort levels: low, high, and max. DeepSeek reports that this release outperforms DeepSeek-V4-Pro (Preview) on its published agentic benchmarks despite its smaller activated parameter count and is broadly competitive with leading proprietary models.
Key model capabilities
- 304B-parameter Mixture-of-Experts architecture
- One-million-token context window for long-context processing
- Attached DSpark speculative decoding module
- Low, high, and max reasoning-effort levels
- Function calling for tool use and agentic workflows
- Strong performance on coding and agentic benchmarks
