What deepseek-flash costs for real workloads
| Workload | Estimated cost |
|---|---|
| Support chatbot: 100K messages | $30.00 |
| RAG search: 10K queries with 6K-token context | $12.00 |
| Batch summarization: 1,000 long documents | $3.60 |
| Coding agent: 100 tasks, 50K context x 20 turns | $2.24 |
Chatbot: 800 input + 300 output tokens per message. RAG: 6,000 + 500 per query. Summarization: 20,000 + 1,000 per document. Coding agent: 20 turns per task over a 50K-token context, with 95% of input served from cache where the model supports it.
deepseek-flash vs similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached / 1M | Blended |
|---|---|---|---|---|---|
| Llama 4 Scout | Groq | $0.11 | $0.34 | — | $0.17 |
| gpt-6-luna | OpenAI | $0.10 | $0.50 | $0.010 | $0.20 |
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.010 | $0.20 |
| Ministral 3 14B | Mistral AI | $0.20 | $0.20 | $0.020 | $0.20 |
| Z.ai GLM 5.3 Flash | Mistral AI | $0.15 | $0.50 | $0.030 | $0.24 |
| GLM-5.3-Flash | Together AI | $0.15 | $0.50 | $0.030 | $0.24 |
| GPT OSS 120B | Groq | $0.15 | $0.60 | — | $0.26 |
| Mistral Small 4 | Mistral AI | $0.15 | $0.60 | $0.015 | $0.26 |
| deepseek-flash | DeepSeek | $0.15 | $0.60 | $0.003 | $0.26 |
Other DeepSeek models
deepseek-flash pricing FAQ
How much does the deepseek-flash API cost?
deepseek-flash costs $0.15 per million input tokens and $0.60 per million output tokens on DeepSeek, with cached input at $0.003 per million. Prices as of November 8, 2026.
How much does deepseek-flash cost for 1,000 requests?
At 1,000 input and 500 output tokens per request, 1,000 requests cost about $0.45.
Does deepseek-flash have a prompt caching discount?
Yes. Cached input is $0.003 per million tokens, 50x cheaper than fresh input. Workloads that resend the same context, like agents and chat with long system prompts, pay mostly the cached rate.
Is deepseek-flash expensive compared to other LLM APIs?
It ranks #15 cheapest of 76 models we track on a blended price (3 input tokens per output token) of $0.26 per million tokens.
Picking a model for production?
Describe your workload and the Planner estimates monthly token spend across every model we track.