DeepSeek V4 Flash (Consensus Protocol)
by LLM Gateway · family deepseek-flash · listed Apr 2026RTW
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Current rates USD per 1M tokens
Input$0.05
Output$0.10
Cache read$0.01
Cache write—
Against the market
On the record
- Model id
consensusprotocol/deepseek-v4-flash- Context window
- 524K tokens
- Max output
- 393K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- May 2025
- Released
- 2026-04-24
- Last updated
- 2026-04-24
- Provider docs
- llmgateway.io/docs
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- SenseNova (China)free in · free out
- Kenarifree in · free out
- Pendrafree in · free out
- InferXfree in · free out
- SCNet Token Planfree in · free out
- Volcengine Ark Coding Planfree in · free out
- NaNfree in · free out
- Alibaba Token Plan (China)free in · free out
- DevPass (LLM Gateway)$0.05 in · $0.10 out
- UnoRouter$0.0625 in · $0.125 out
- OpenRouter$0.0899 in · $0.18 out
- Deep Infra$0.09 in · $0.18 out
- TokenGo$0.098 in · $0.196 out
- Modelis$0.0983 in · $0.197 out