DeepSeek V4.1 Flash 1017
aiand/deepseek-ai/deepseek-v4.1-flash-1017 · family deepseek-flash · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$0.38
Blended $/1M (3:1)
$0.3
Input $/1M
$0.6
Output $/1M
$0.90
1M in + 1M out
$0.02 −93%
Cache read $/1M
#2626 of 8,491
Cheapest rank
- Provider
- ai& (
aiand) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“DeepSeek V4.1 Flash 1017” is offered by 37 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Token Plan | free | free | $0.00 | 1M |
| Umans AI Coding Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| engy | $0.03 | $0.12 | $0.05 | 1M |
| Vercel AI Gateway | $0.075 | $0.3 | $0.13 | 1M |
| NanoGPT | $0.1 | $0.6 | $0.23 | 1M |
| OpenRouter | $0.15 | $0.6 | $0.26 | 1M |
| Merge Gateway | $0.15 | $0.6 | $0.26 | 1M |
| DevPass (LLM Gateway) | $0.15 | $0.6 | $0.26 | 1.1M |
| Umans AI | $0.15 | $0.6 | $0.26 | 1M |
| Ollama Cloud | $0.15 | $0.6 | $0.26 | 1M |
| DeepSeek | $0.15 | $0.6 | $0.26 | 1M |
| ai& (this) | $0.3 | $0.6 | $0.38 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at 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-ai/deepseek-v4.1-flash-1017","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):