DeepSeek V4.1 Flash TEE

DeepSeek V4.1 Flash's October 17, 2026 checkpoint (1017) supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This route runs through Tinfoil attested inference inside a Trusted Execution Environment. Tinfoil lists this model as experimental, with availability subject to change.

Reasoning
Vision
Tool Calling
Parallel Tool Calls
Structured Output

Added Sep 12, 2026

Pricing

Auto routing · per 1M tokens

Input: $0.65
Output: $1.45
Cache read: $0.13

Compare provider prices

Specifications

Context window: 1M
Max output: 384K
Avg output (7d): 581 tokens; Longer than 54% of models

Benchmarks

Artificial Analysis

Design Arena

Sourced from Artificial Analysis.

Intelligence Index

24.7

Better than 77% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

47.8%

Better than 62% of models compared

AutomationBench-AA Tasks Completed

Fully completed workflows without guardrail violations

14.2%

Better than 58% of models compared

AA-Briefcase v1.1

Agentic knowledge work (Elo)

1118 Elo

Better than 56% of models compared

GDPval-AA v2.1

Economically valuable tasks (Elo)

1339 Elo

Better than 69% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

3.8%

Better than 22% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

55.3%

Better than 47% of models compared

Reasoning

HLE

Humanity's Last Exam

10.8%

Better than 51% of models compared

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

5.6%

Better than 55% of models compared

SciCode

Python programming for scientific computing

35.5%

Better than 13% of models compared

Legacy benchmarks

AA-LCR (unversioned / legacy)

Long context reasoning evaluation