Tri-21B-Think: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
Tri-21B-Think supports text input, outputs text, and has a 32k tokens context window.
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 32k ~48 A4 pages of size 12 Arial font |
| Total parameters | 21B |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Tri-21B-Think | - | 21B | 32k | - | - | - | - |
Frequently Asked Questions
Common questions about Tri-21B-Think
Tri-21B-Think was released on February 10, 2026.
Tri-21B-Think was created by Trillion Labs.
Yes, Tri-21B-Think is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Tri-21B-Think supports text input.
Tri-21B-Think supports text output.
No, Tri-21B-Think does not support image input. It can only process text.
No, Tri-21B-Think is not multimodal. It only supports text input.
Tri-21B-Think has a context window of 32k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Tri-21B-Think is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Tri-21B-Think has 21B parameters.
Tri-21B-Think is released under the Apache 2.0 license. This license allows commercial use. View license
Tri-21B-Think is an open weights model that can be self-hosted. View providers
Tri-21B-Think is an open weights model that can be downloaded and self-hosted. Compare providers