deepseek-v4-flash is the recommended option for voice agents — very low cost per token, high concurrent request limits, and competitive quality for conversational tasks.
Quick config
Supported models
Recommendation: Use
deepseek-v4-flash for all new deployments. It supports up to 2,500 concurrent requests — well-suited for high-volume outbound campaigns.
Key settings
Prompt caching
DeepSeek V4 models support prompt caching — repeated system prompts cost significantly less on cache hits. For agents that run many calls with the same system prompt, this can reduce LLM costs substantially. Cache hits are automatic; no configuration needed.FAQ
deepseek-v4-flash vs deepseek-v4-pro — which should I use?
deepseek-v4-flash vs deepseek-v4-pro — which should I use?
Use
deepseek-v4-flash for most agents — lower cost, higher concurrency (2,500 vs 500 requests), and lower latency. Switch to deepseek-v4-pro if your use case requires more complex reasoning (e.g., nuanced financial conversations, detailed troubleshooting).How do I migrate from deepseek-chat?
How do I migrate from deepseek-chat?
Change
"model": "deepseek-chat" to "model": "deepseek-v4-flash" in your agent’s LLM config. The API is compatible — no other changes needed. Test your prompt to confirm behavior since V4 is a newer generation.How does DeepSeek compare to OpenAI for voice?
How does DeepSeek compare to OpenAI for voice?
DeepSeek V4 is significantly cheaper and has a 1M token context window. For simple to moderate conversational tasks (reminders, qualification, COD confirmation), quality is comparable. For complex reasoning or precise instruction-following in English, GPT-5.4-mini may have an edge. Test on your specific use case.
Related
- LLM Tab — configure LLM in the dashboard
- OpenAI — GPT-5 family alternative
- OpenRouter — access DeepSeek and others via unified gateway
- Prompting Guide — write effective prompts for voice