Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Experimental vision-enabled release of DeepSeek V4 Flash (open weights, MIT, 305B MoE) — the same efficiency tier with image input. DeepSeek labels it experimental; expect the id to move when a stable release lands.
deepseek-v4-flash-vision-exp — Experimental vision-enabled release of DeepSeek V4 Flash (open weights, MIT, 305B MoE) — the same efficiency tier with image input. DeepSeek labels it experimental; expect the id to move when a stable release lands.
| Field | Value |
|---|---|
| Model ID | deepseek-v4-flash-vision-exp |
| Best for | Cheap multimodal reasoning on the V4 Flash line |
| Context window | 1.048576M |
| Max output tokens | 384K |
| Input modalities | Text, Image |
| Output modalities | Text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Prompt caching | No |
| Speed | Fast |
| Cost band | Cheap |
| Release stage | Preview |
| Per 1M tokens | |
|---|---|
| Input | $0.297 |
| Output | $0.891 |
from openai import OpenAI
client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")
response = client.chat.completions.create(
model="deepseek-v4-flash-vision-exp",
messages=[{"role": "user", "content": "..."}],
tools=[...], # function calling supported
)
curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=efficient"