Compare models
Add a modelContext is the model author's published window. Independent's context and output limits are not verified.
| Attribute | |
|---|---|
| Overview | A version of DeepSeek V4.1 Flash with its refusal behavior removed (abliterated) by the independent provider that runs it. It answers many requests the original model declines. The change was not made by DeepSeek. |
| Context (model) | 1,048,576 |
| Max output (route) | 65,536 |
| Released | Sep 10, 2026 |
| Input / output | text, image → text |
| Pricing | USD per 1M tokens |
| Input / 1M | $0.125 |
| Output / 1M | $0.50 |
| Status | Available |
| Features | Tool calling Image input Streaming JSON mode |
| Uptime (30 days) | 99.47% of 948 requests |
| First token (typical) | 1.53 s |
| Output speed (typical) | 37.2 tokens/s |
| Endpoints | 1 |
Uptime is the share of real requests and Zalmir's own small test requests that got an answer over the last 30 days (UTC). Typical speed is the median over the same days. Each shows once at least 20 requests were made.