DeepSeek V4 Flash Vision Exp
vercel/deepseek/deepseek-v4-flash-vision-exp · family deepseek-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.32
Blended $/1M (3:1)
$0.2156
Input $/1M
$0.6468
Output $/1M
$0.86
1M in + 1M out
$0.0068 −97%
Cache read $/1M
#2368 of 7,920
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 1,048,576 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“DeepSeek V4 Flash Vision Exp” is offered by 17 providers — cheapest-effective first. CrofAI is the cheapest at $0.11 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| CrofAI | $0.08 | $0.2 | $0.11 | 1M |
| OpenCode Zen | $0.14 | $0.28 | $0.18 | 1M |
| AMD | $0.14 | $0.28 | $0.18 | 1M |
| OrcaRouter | $0.147 | $0.295 | $0.18 | 1M |
| DeepSeek | $0.15 | $0.6 | $0.26 | 1M |
| OpenCode Go | $0.15 | $0.6 | $0.26 | 1M |
| Eden AI | $0.15 | $0.6 | $0.26 | 1M |
| AIHubMix | $0.155 | $0.62 | $0.27 | 1M |
| Vercel AI Gateway (this) | $0.2156 | $0.6468 | $0.32 | 1M |
| OpenRouter | $0.2156 | $0.6468 | $0.32 | 1M |
| NanoGPT | $0.22 | $0.66 | $0.33 | 1M |
| CrossModel | $0.3 | $1.2 | $0.52 | 1M |
| Deep Infra | $0.44 | $1.32 | $0.66 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v4-flash-vision-exp","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):