TNG: DeepSeek R1T2 Chimera

Text input Text output
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...

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

This model supports the following parameters:

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

This model supports the following features:

Reasoning
Performance Summary

TNG: DeepSeek R1T2 Chimera, a 671B-parameter mixture-of-experts model, demonstrates exceptional performance across several key metrics. It consistently ranks among the fastest models available, achieving an Infinityth percentile speed ranking across five benchmarks, and offers highly competitive pricing, also at the Infinityth percentile. The model exhibits outstanding reliability with a 100% success rate across all benchmarks, indicating minimal technical failures. In terms of benchmark performance, DeepSeek R1T2 Chimera excels in knowledge-based and classification tasks. It achieved perfect 100% accuracy in General Knowledge, Email Classification, and Ethics benchmarks, often being the most accurate model at its price point and speed. Its Coding performance is also strong, with 95.0% accuracy, placing it in the 93rd percentile. A notable weakness is observed in the Instruction Following (Baseline) benchmark, where it recorded 0.0% accuracy, suggesting a significant area for improvement in complex, multi-layered instruction adherence. Despite this, its tri-parent design contributes to strong reasoning and a favorable cost-to-intelligence trade-off, running significantly faster than its predecessors. The model also supports long contexts up to 60k tokens, making it suitable for extensive analysis.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $1.1
Input Cache Read $0.15

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Chutes
Chutes | tngtech/deepseek-r1t2-chimera 163K $0.3 / 1M tokens $1.1 / 1M tokens
Chutes
Chutes | tngtech/deepseek-r1t2-chimera 163K $0.3 / 1M tokens $1.1 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by tngtech