DeepSeek V4 Flash Latest
arcee/deepseek/deepseek-v4-flash-latest · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.18
Blended $/1M (3:1)
$0.14
Input $/1M
$0.28
Output $/1M
$0.42
1M in + 1M out
$0.028 −80%
Cache read $/1M
#1240 of 6,245
Cheapest rank
- Provider
- Arcee (
arcee) - 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 Latest” is offered by 4 providers — cheapest-effective first. OpenRouter is the cheapest at $0.10 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenRouter | $0.0783 | $0.1566 | $0.10 | 1.3M |
| Kilo Gateway | $0.0783 | $0.1566 | $0.10 | 262k |
| Arcee (this) | $0.14 | $0.28 | $0.18 | 1M |
| NanoGPT | $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 Arcee 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):