DeepSeek V4 Flash 0731
adaption/deepseek-v4-flash · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.07
Blended $/1M (3:1)
$0.0444
Input $/1M
$0.1333
Output $/1M
$0.18
1M in + 1M out
$0.001414 −97%
Cache read $/1M
#791 of 9,563
Cheapest rank
- Provider
- Adaption (
adaption) - 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 0731” is offered by 59 providers — cheapest-effective first. Alibaba Token Plan (China) is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| AMD | free | free | $0.00 | 1M |
| JoinGonka | $0.006171 | $0.0185 | $0.01 | 380k |
| SAGG | $0.0397 | $0.0794 | $0.05 | 400k |
| engy | $0.045 | $0.09 | $0.06 | 1M |
| Adaption (this) | $0.0444 | $0.1333 | $0.07 | 1M |
| NanoGPT | $0.05 | $0.16 | $0.08 | 1M |
| Boundless | $0.04 | $0.21 | $0.08 | 1M |
| Deep Infra | $0.06 | $0.18 | $0.09 | 1M |
| OpenRouter | $0.0434 | $0.3 | $0.11 | 1M |
| Doubleword | $0.09 | $0.18 | $0.11 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Adaption 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):