Available Models in Tinker

The table below shows the models that are currently available in Tinker. We plan to update this list as new models are released.

What model should I use?

In general, use MoE models, which are more cost effective than the dense models.
Use Base models only if you're doing research or are running the full post-training pipeline yourself
If you want to create a model that is good at a specific task or domain, use an existing post-trained model, and fine-tune it on your own data or environment.
- If you care about latency, use one of the Instruction models, which will start outputting tokens without a chain-of-thought.
- If you care about intelligence and robustness, use one of the Hybrid or Reasoning models, which can use long chain-of-thought.

Full Listing

Model Name	Training Type	Architecture	Size
Qwen/Qwen3.5-397B-A17B	Hybrid + Vision	MoE	Large
Qwen/Qwen3.5-35B-A3B	Hybrid + Vision	MoE	Medium
Qwen/Qwen3.5-27B	Hybrid + Vision	Dense	Medium
Qwen/Qwen3.5-4B	Hybrid + Vision	Dense	Compact
Qwen/Qwen3-VL-235B-A22B-Instruct	Vision	MoE	Large
Qwen/Qwen3-VL-30B-A3B-Instruct	Vision	MoE	Medium
Qwen/Qwen3-235B-A22B-Instruct-2507	Instruction	MoE	Large
Qwen/Qwen3-30B-A3B-Instruct-2507	Instruction	MoE	Medium
Qwen/Qwen3-30B-A3B	Hybrid	MoE	Medium
Qwen/Qwen3-30B-A3B-Base	Base	MoE	Medium
Qwen/Qwen3-32B	Hybrid	Dense	Medium
Qwen/Qwen3-8B	Hybrid	Dense	Small
Qwen/Qwen3-8B-Base	Base	Dense	Small
Qwen/Qwen3-4B-Instruct-2507	Instruction	Dense	Compact
openai/gpt-oss-120b	Reasoning	MoE	Medium
openai/gpt-oss-20b	Reasoning	MoE	Small
deepseek-ai/DeepSeek-V3.1	Hybrid	MoE	Large
deepseek-ai/DeepSeek-V3.1-Base	Base	MoE	Large
meta-llama/Llama-3.1-70B	Base	Dense	Large
meta-llama/Llama-3.3-70B-Instruct	Instruction	Dense	Large
meta-llama/Llama-3.1-8B	Base	Dense	Small
meta-llama/Llama-3.1-8B-Instruct	Instruction	Dense	Small
meta-llama/Llama-3.2-3B	Base	Dense	Compact
meta-llama/Llama-3.2-1B	Base	Dense	Compact
moonshotai/Kimi-K2-Thinking	Reasoning	MoE	Large
moonshotai/Kimi-K2.5	Reasoning + Vision	MoE	Large

Legend

Training Types

Base: Foundation models trained on raw text data, suitable for post-training research and custom fine-tuning.
Instruction: Models fine-tuned for following instructions and chat, optimized for fast inference.
Reasoning: Models that always use chain-of-thought reasoning before their "visible" output that responds to the prompt.
Hybrid: Models that can operate in both thinking and non-thinking modes, where the non-thinking mode requires using a special renderer or argument that disables chain-of-thought.
Vision: Vision-language models (VLMs) that can process images alongside text. See Vision Inputs for usage.

Architecture

Dense: Standard transformer architecture with all parameters active
MoE: Mixture of Experts architecture with sparse activation

Model Sizes

Compact: 1B-4B parameters
Small: 8B parameters
Medium: 30B-32B parameters
Large: 70B+ parameters

Note that the MoE models are much more cost effective than the dense models as their cost is proportional to the number of active parameters and not the total number of parameters.

Async and Futures ServiceClient