DeepSeek V4.1 Flash Uncensored
nokeep/deepseek-v4.1-flash-uncensored · family deepseek-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.78
Blended $/1M (3:1)
$0.45
Input $/1M
$1.75
Output $/1M
$2.20
1M in + 1M out
$0.011 −98%
Cache read $/1M
#4394 of 9,563
Cheapest rank
- Provider
- nokeep (
nokeep) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“DeepSeek V4.1 Flash Uncensored” is offered by 3 providers — cheapest-effective first. NanoGPT is the cheapest at $0.58 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.33 | $1.32 | $0.58 | 1M |
| Venice AI | $0.33 | $1.32 | $0.58 | 1M |
| nokeep (this) | $0.45 | $1.75 | $0.78 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at nokeep 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-uncensored","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):