TNG: DeepSeek R1T2 Chimera

Text input Text output Unavailable Free Option
Author's Description

DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The tri-parent design yields strong reasoning performance while running roughly 20 % faster than the original R1 and more than 2× faster than R1-0528 under vLLM, giving a favorable cost-to-intelligence trade-off. The checkpoint supports contexts up to 60 k tokens in standard use (tested to ~130 k) and maintains consistent <think> token behaviour, making it suitable for long-context analysis, dialogue and other open-ended generation tasks.

Key Specifications
Cost
$$$$
Context
163K
Parameters
1T
Released
Jul 08, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Logit Bias Temperature Seed Frequency Penalty Max Tokens Include Reasoning Top P Min P Reasoning Logprobs Top Logprobs
Features

This model supports the following features:

Reasoning
Performance Summary

TNG: DeepSeek R1T2 Chimera, a 671B-parameter mixture-of-experts model, consistently ranks among the fastest models available and offers highly competitive pricing, demonstrating an exceptional cost-to-intelligence trade-off. Its reliability is outstanding, with a 100th percentile ranking across all benchmarks, indicating minimal technical failures. The model excels in accuracy across several critical areas, achieving perfect scores in Ethics, Email Classification, and General Knowledge, often being the most accurate at its price point and speed. It also shows strong performance in Coding (95.0% accuracy) and Reasoning (86.0% accuracy). A notable weakness is its performance in Instruction Following, where it recorded 0.0% accuracy, suggesting this area requires significant improvement. Despite this, its overall speed, cost-efficiency, and high accuracy in key domains make it a compelling choice for long-context analysis, dialogue, and open-ended generation tasks, particularly given its consistent <think> token behavior and support for contexts up to 60k tokens.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.302
Completion $0.302

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Chutes
Chutes | tngtech/deepseek-r1t2-chimera 163K $0.302 / 1M tokens $0.302 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by tngtech