deepseek-v4-flash
by Ollama Cloud · family deepseek-flash · listed Apr 2026RTW
Fast DeepSeek model for efficient chat, coding help, and agent loops
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
deepseek-v4-flash- Context window
- 1.0M tokens
- Max output
- 1.0M tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-04-24
- Last updated
- 2026-04-24
- Provider docs
- docs.ollama.com/cloud
Also listed at
- Alibaba Token Planfree in · free out
- Kenarifree in · free out
- InferXfree in · free out
- SCNet Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- UnoRouter$0.0625 in · $0.125 out
- LLM Gateway$0.075 in · $0.175 out
- DevPass (LLM Gateway)$0.076 in · $0.153 out
- OpenRouter$0.0826 in · $0.165 out
- Deep Infra$0.09 in · $0.18 out
- Modelis$0.0983 in · $0.197 out
- Pioneer$0.10 in · $0.20 out
- Neuralwatt$0.104 in · $0.207 out
- routing.run$0.112 in · $0.224 out
- GMI Cloud$0.112 in · $0.224 out