DeepSeek V4 Flash Latest
nano-gpt/deepseek/deepseek-v4-flash-latest · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.08
Blended $/1M (3:1)
$0.05
Input $/1M
$0.16
Output $/1M
$0.21
1M in + 1M out
$0.013 −74%
Cache read $/1M
#839 of 7,717
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4 Flash Latest” is offered by 3 providers — cheapest-effective first. This one (NanoGPT) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT (this) | $0.05 | $0.16 | $0.08 | 1M |
| OpenRouter | $0.022 | $0.32 | $0.10 | 1.3M |
| Arcee | $0.14 | $0.28 | $0.18 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v4-flash-latest","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):