DeepSeek V4 Flash
inferenceapis/deepseek-ai/DeepSeek-V4-Flash · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.24
Blended $/1M (3:1)
$0.19
Input $/1M
$0.38
Output $/1M
$0.57
1M in + 1M out
$0.04 −79%
Cache read $/1M
#2121 of 9,232
Cheapest rank
- Provider
- Inference APIs (
inferenceapis) - 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” is offered by 56 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 |
| UnoRouter | free | free | $0.00 | 1M |
| Pendra | free | free | $0.00 | 1M |
| SenseNova (China) | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| Umans AI Coding Plan | free | free | $0.00 | 1M |
| Volcengine Ark Coding Plan | free | free | $0.00 | 1M |
| SCNet 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 |
| OpenRouter | $0.09 | $0.18 | $0.11 | 1M |
| Inference APIs (this) | $0.19 | $0.38 | $0.24 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Inference APIs 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):