Capabilities
7-day heat trend
−17.4%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 9% of tracked models
- Faster than 30% of tracked models
- Efficiency rank: #891 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About accounts/fireworks/models/deepseek-v4-pro
DeepSeek V4 Pro on Fireworks is a higher-capability serverless model for reasoning and coding.
accounts/fireworks/models/deepseek-v4-pro is a Text model from Fireworks AI (US). HotON.ai tracks it at $1.74 per 1M input tokens and $3.48 per 1M output tokens, with a 131K-token context window, ~138 tokens/sec throughput and 96.7% availability. Its composite efficiency score is 88/100 at an estimated $0.005 per successful task.
Compare accounts/fireworks/models/deepseek-v4-pro
Related market news
Frequently asked questions
How much does accounts/fireworks/models/deepseek-v4-pro cost per 1M tokens?+
accounts/fireworks/models/deepseek-v4-pro is tracked at $1.74 per 1M input tokens and $3.48 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $3.04 per 1M tokens. Figures are illustrative demo data.
What is accounts/fireworks/models/deepseek-v4-pro best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is accounts/fireworks/models/deepseek-v4-pro?+
accounts/fireworks/models/deepseek-v4-pro delivers about 138 tokens/sec with 96.7% tracked availability, suitable for latency-sensitive, real-time applications.
Is accounts/fireworks/models/deepseek-v4-pro cheaper than other AI models?+
Within the HotON.ai tracked set, accounts/fireworks/models/deepseek-v4-pro is cheaper than 9% of models on input price and ranks #891 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.