DeepSeek V4.1 Flash
empiriolabs/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
$0.3
Cache read $/1M
#2740 of 7,323
Cheapest rank
- Provider
- EmpirioLabs AI (
empiriolabs) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 393,216 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“DeepSeek V4.1 Flash” is offered by 31 providers — cheapest-effective first. NaN is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NaN | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| NanoGPT | $0.1 | $0.4 | $0.18 | 1M |
| AMD | $0.14 | $0.28 | $0.18 | 1M |
| Vercel AI Gateway | $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 |
| ClinePass | $0.15 | $0.6 | $0.26 | 1M |
| 302.AI | $0.15 | $0.6 | $0.26 | 1M |
| OpenCode Go | $0.15 | $0.6 | $0.26 | 1M |
| EmpirioLabs AI (this) | $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 EmpirioLabs AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-1-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):