DeepSeek V4 Flash Vision Exp (DeepInfra) API
DeepInfra · serves deepseek-v4-flash-vision-exp
Pricing
| Input / 1M | $0.22 |
|---|---|
| Output / 1M | $0.65 |
| Blended / 1M | $0.862cheapest of 4 |
| Cached input / 1M | $0.07 |
| Context window | 1,048,576 tokens |
| Max output | 131,072 tokens |
| License | Open weights · MIT permissive |
| Knowledge cutoff | March 2026 · source |
textvisionfunction-calling
Price verified 2026-09-05 (0 days ago) · sourcetier mismatch?
Sources
The two sources differ by about 104% — close to an exact 2× ratio, which usually means one source lists a different pricing tier (e.g. batch vs standard) rather than a real disagreement. The figure above is the primary source.
| Source | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| OpenRouter | $0.22 | $0.65 | 2026-09-05 |
| LiteLLM | $0.44 | $1.32 | 2026-09-03 |
| models.dev | $0.44 | $1.32 | 2026-09-04 |
Call it
Served via OpenRouter, pinned to DeepInfra — the provider these prices are resolved from. Set OPENROUTER_API_KEY. Provider page.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash-vision-exp",
"messages": [{"role": "user", "content": "Hello"}],
"provider": {"only": ["DeepInfra"], "allow_fallbacks": false}
}'from openai import OpenAI # pip install openai
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="...", # OPENROUTER_API_KEY
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-flash-vision-exp",
messages=[{"role": "user", "content": "Hello"}],
extra_body={"provider": {"only": ["DeepInfra"], "allow_fallbacks": false}},
)
print(resp.choices[0].message.content)Price unchanged since 2026-09-03 — 1 point on record.
Use this data
Raw JSON for this page: deepseek-v4-flash-vision-exp.json. Free to reuse under CC BY 4.0 with attribution to apipriceindex.com.