deepseek-chat

deepseek-chat is a efficient-tier language model from DeepSeek with 671B parameters. deepseek-chat is an open-weights model, meaning the weights are publicly available for self-hosting, fine-tuning, and deployment on your own infrastructure — not just through DeepSeek's API. DeepSeek is a Chinese AI lab's open-weights model family, known for competitive performance at very low API prices — particularly strong on coding and math benchmarks.

deepseek-chat is priced at $0.27/1M input tokens and $1.1/1M output tokens. Output tokens are 4.1× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, deepseek-chat costs approximately $0.82 per 1,000 API calls. Prompt caching reduces repeated input tokens to $0.07/1M — a 74% discount that compounds significantly for applications with long shared system prompts, multi-turn conversations, or document Q&A where the same context is reused across many queries.

Its 66K-token context window is sufficient for most production use cases, handling documents up to ~25,000 words or multi-turn conversations spanning dozens of exchanges. Median latency (P50 time-to-first-token) is approximately 600ms — suitable for interactive applications where sub-second response is acceptable. Throughput is approximately 90 tokens/second — adequate for streaming at comfortable reading speed. Maximum output length is 8K tokens — adequate for most generation tasks including essays, code functions, and detailed responses.

deepseek-chat is best suited to coding, chat, cost. Supported capabilities include function calling / tool use for agentic workflows, streaming token output for real-time UIs. Function calling support makes it suitable for building AI agents, structured data extraction pipelines, and any workflow requiring the model to invoke external APIs or return typed JSON. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how deepseek-chat compares to similar models across these dimensions.

deepseek-chat sits in the efficient tier — optimized for speed and cost while maintaining solid quality, ideal for high-volume or latency-sensitive workloads. As an open-weights model, deepseek-chat can be self-hosted on GPU compute (see the GPU rental comparison on this site) to eliminate per-token API costs entirely — the break-even point versus API pricing depends on your volume and the GPU hourly rate. When comparing deepseek-chat to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (74/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.