DeepSeek V4.1 Flash
huggingface/deepseek-ai/DeepSeek-V4.1-Flash · family deepseek-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.52
Blended $/1M (3:1)
$0.3
Input $/1M
$1.2
Output $/1M
$1.50
1M in + 1M out
—
Cache read $/1M
#2652 of 7,160
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 V4.1 Flash” is offered by 14 providers — cheapest-effective first. NanoGPT is the cheapest at $0.26 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.15 | $0.6 | $0.26 | 1M |
| DevPass (LLM Gateway) | $0.15 | $0.6 | $0.26 | 1.1M |
| Merge Gateway | $0.15 | $0.6 | $0.26 | 1M |
| DeepSeek | $0.15 | $0.6 | $0.26 | 1M |
| OpenRouter | $0.15 | $0.6 | $0.26 | 1M |
| OpenCode Go | $0.15 | $0.6 | $0.26 | 1M |
| CrossModel | $0.27 | $1.08 | $0.47 | 1M |
| Hugging Face (this) | $0.3 | $1.2 | $0.52 | 1M |
| Requesty | $0.3 | $1.2 | $0.52 | 1M |
| Vercel AI Gateway | $0.3 | $1.2 | $0.52 | 1M |
| Deep Infra | $0.3 | $1.2 | $0.52 | 1M |
| Kilo Gateway | $0.3 | $1.2 | $0.52 | 1M |
| Ofox | $0.3 | $1.2 | $0.52 | 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-V4.1-Flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):