DeepSeek V4 Flash 0423
wafer.ai/DeepSeek-V4-Flash-0423 · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.18
Blended $/1M (3:1)
$0.14
Input $/1M
$0.28
Output $/1M
$0.42
1M in + 1M out
$0.028 −80%
Cache read $/1M
#1585 of 9,563
Cheapest rank
- Provider
- Wafer (
wafer.ai) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4 Flash 0423” is offered by 6 providers — cheapest-effective first. Venice AI is the cheapest at $0.17 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Venice AI | $0.138 | $0.275 | $0.17 | 1M |
| Merge Gateway | $0.139 | $0.278 | $0.17 | 131k |
| Wafer (this) | $0.14 | $0.28 | $0.18 | 1M |
| NanoGPT | $0.14 | $0.28 | $0.18 | 1M |
| Ofox | $0.19 | $0.51 | $0.27 | 1M |
| Prime Inference | $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 Wafer 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-Flash-0423","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):