DeepSeek V4 Flash (deepseek-v4-flash) is a chat model from deepseek with a 1M-token context window; open-weight; capabilities tools, vision, reasoning; input image, text; output text.
1MContext
393.2KMax output
$0.3$ / 1M in
128.05tok / s
Pricing
Input
$0.3 / 1M tokens
Output
$1.2 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-10-30.
Performance
Throughput
128.05 tokens/s
Latency (TTFT)
1.55 s
Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-11-05.