DeepSeek V4 Flash 0731
siliconflow/deepseek-ai/DeepSeek-V4-Flash-0731 · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.33
Blended $/1M (3:1)
$0.22
Input $/1M
$0.66
Output $/1M
$0.88
1M in + 1M out
$0.014 −94%
Cache read $/1M
#2497 of 8,511
Cheapest rank
- Provider
- SiliconFlow (
siliconflow) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4 Flash 0731” is offered by 48 providers — cheapest-effective first. SCNet Token Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| SCNet Token Plan | free | free | $0.00 | 1M |
| AMD | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| Merge Gateway | $0.035 | $0.07 | $0.04 | 1M |
| engy | $0.045 | $0.09 | $0.06 | 1M |
| NanoGPT | $0.0458 | $0.1373 | $0.07 | 1M |
| Boundless | $0.04 | $0.21 | $0.08 | 1M |
| Deep Infra | $0.06 | $0.18 | $0.09 | 1M |
| OpenRouter | $0.0448 | $0.3 | $0.11 | 1M |
| Munito AI | $0.099 | $0.25 | $0.14 | 1M |
| Vultr | $0.1 | $0.25 | $0.14 | 1M |
| SiliconFlow (this) | $0.22 | $0.66 | $0.33 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at SiliconFlow 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-Flash-0731","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):