All LLM prices / DeepSeek
deepseek-v4-flash price per 1M tokens
deepseek-v4-flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, and $0.00600 per 1M cached input tokens read.
| Per 1M tokens | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| deepseek-v4-flash | $0.30 | $1.20 | $0.00600 | — |
What a call costs
A typical agent step of 20,000 input and 1,500 output tokens costs $0.00780 on deepseek-v4-flash, so 10,000 of them a month is $78.00. Serving the repeated part of the prompt from cache cuts the input side to $0.00600 per 1M.
deepseek-v4-flash on other providers
| Listed as | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| aihubmix/deepseek-v4-flash | $0.142 | $0.284 | $0.0284 | — |
| azure_ai/deepseek-v4-flash | $0.19 | $0.51 | $0.028 | — |
| dashscope/deepseek-v4-flash | $0.20 | $0.40 | $0.04 | — |
| deepseek/deepseek-v4-flash | $0.30 | $1.20 | $0.00600 | — |
| fireworks_ai/accounts/fireworks/models/deepseek-v4-flash | $0.14 | $0.28 | $0.028 | — |
| fireworks_ai/deepseek-v4-flash | $0.14 | $0.28 | $0.028 | — |
| inferenceapis/deepseek-v4-flash | $0.19 | $0.38 | $0.04 | — |
| libertai/deepseek-v4-flash | $0.25 | $1.75 | — | — |
| novita/deepseek/deepseek-v4-flash | $0.14 | $0.28 | $0.028 | — |
| openrouter/deepseek/deepseek-v4-flash | $0.028 | $0.056 | $0.00560 | — |
| pinstripes/ps/deepseek-v4-flash | $0.10 | $0.20 | — | — |
| prism/deepseek-v4-flash | $0.17 | $0.21 | $0.07 | — |
| qwen_ai_platform/deepseek-v4-flash | $0.20 | $0.40 | $0.04 | — |
| qwencloud/deepseek-v4-flash | $0.20 | $0.40 | $0.04 | — |
| tencent/deepseek-v4-flash | $0.14 | $0.28 | $0.00280 | — |
Price history
No change to the listed rates since this log began on 2026-10-04.
Price a call with the free API
No key, no account. It uses this same table, and with "usage_shape": "openai" it takes the cached tokens out of prompt_tokens first, so they aren't billed twice.
curl -s https://api.aight.studio/api/cost \
-H 'content-type: application/json' \
-d '{"model": "deepseek-v4-flash", "input_tokens": 20000, "output_tokens": 1500, "cache_read_tokens": 12000}'
Returns cost_usd, a breakdown per token type, the rates per 1M, and when the table last changed. Rates only: GET https://api.aight.studio/api/pricing?models=a,b. Rate-limited per client; an unknown model is a 404, never $0. Full API docs.
pip install aight && aight-collect --report prices your Claude Code, Codex or Gemini CLI history locally with no account.