DeepSeek V4 Flash Vision Exp
huggingface/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp · family deepseek-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.66
Blended $/1M (3:1)
$0.44
Input $/1M
$1.32
Output $/1M
$1.76
1M in + 1M out
—
Cache read $/1M
#3646 of 8,566
Cheapest rank
- Provider
- Hugging Face (
huggingface) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“DeepSeek V4 Flash Vision Exp” is offered by 16 providers — cheapest-effective first. AMD is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| AMD | free | free | $0.00 | 1M |
| OpenCode | $0.14 | $0.28 | $0.18 | 1M |
| Eden AI | $0.15 | $0.6 | $0.26 | 1M |
| CommandCode | $0.15 | $0.6 | $0.26 | 1M |
| DeepSeek | $0.15 | $0.6 | $0.26 | 1M |
| AIHubMix | $0.155 | $0.62 | $0.27 | 1M |
| NanoGPT | $0.2156 | $0.6468 | $0.32 | 1M |
| Vercel AI Gateway | $0.2156 | $0.6468 | $0.32 | 1M |
| OrcaRouter | $0.22 | $0.66 | $0.33 | 1M |
| CrossModel | $0.3 | $1.2 | $0.52 | 1M |
| Hugging Face (this) | $0.44 | $1.32 | $0.66 | 1M |
| Deep Infra | $0.44 | $1.32 | $0.66 | 1M |
| AI/ML API | $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 Hugging Face and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-ai/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):