DeepSeek V4.1 Flash
thinkingmachines/deepseek-ai/DeepSeek-V4.1-Flash:peft:262144 · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.35
Blended $/1M (3:1)
$0.6
Input $/1M
$3.6
Output $/1M
$4.20
1M in + 1M out
$0.12 −80%
Cache read $/1M
#4891 of 8,512
Cheapest rank
- Provider
- Thinking Machines (
thinkingmachines) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4.1 Flash” is offered by 65 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 |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Nvidia | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| AMD | free | free | $0.00 | 1M |
| Umans AI Coding Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| NaN | free | free | $0.00 | 1M |
| engy | $0.03 | $0.12 | $0.05 | 1M |
| NanoGPT | $0.022 | $0.4 | $0.12 | 1M |
| ZenMux | $0.075 | $0.3 | $0.13 | 1M |
| OpenRouter | $0.051 | $0.567 | $0.18 | 1M |
| Thinking Machines (this) | $0.6 | $3.6 | $1.35 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Thinking Machines 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-V4.1-Flash:peft:262144","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):