DeepSeek V4 Flash
vivgrid/deepseek-v4-flash · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.66
Blended $/1M (3:1)
$0.44
Input $/1M
$1.32
Output $/1M
$1.76
1M in + 1M out
$0.044 −90%
Cache read $/1M
#3610 of 8,512
Cheapest rank
- Provider
- Vivgrid (
vivgrid) - 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” is offered by 50 providers — cheapest-effective first. SenseNova (China) is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| SenseNova (China) | free | free | $0.00 | 1M |
| Pendra | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Volcengine Ark Coding Plan | free | free | $0.00 | 1M |
| UnoRouter | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| Umans AI Coding Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| DevPass (LLM Gateway) | $0.076 | $0.153 | $0.10 | 1.1M |
| Standard Compute | $0.0826 | $0.1652 | $0.10 | 1M |
| Deep Infra | $0.09 | $0.18 | $0.11 | 1M |
| Kilo Gateway | $0.091 | $0.182 | $0.11 | 1M |
| Vivgrid (this) | $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 Vivgrid 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):