Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.primeintellect.ai/llms.txt

Use this file to discover all available pages before exploring further.

Hosted Training supports a range of open-weights models. This page lists the currently available models, their pricing, and guidance on choosing the right model for your use case.

​
Available Models

Prices are per million tokens, billed separately for input, output, and training. Prefix cache hits receive automatically-applied discounts.
ModelInput ($ / 1M)Output ($ / 1M)Train ($ / 1M)
Qwen/Qwen3.5-0.8B0.020.060.06
Qwen/Qwen3.5-2B0.050.150.15
Qwen/Qwen3.5-4B0.100.300.30
Qwen/Qwen3.5-9B0.200.600.60
Qwen/Qwen3.5-35B-A3B0.250.751.00
Qwen/Qwen3.5-122B-A10B0.501.502.00
Qwen/Qwen3.5-397B-A17B1.003.004.00
meta-llama/Llama-3.2-1B-Instruct0.020.060.06
meta-llama/Llama-3.2-3B-Instruct0.050.150.15
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF160.150.450.60
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF160.300.901.20
openai/gpt-oss-20b0.100.300.40
openai/gpt-oss-120b0.250.751.00

​
Choosing a Model

​
For Validation and Debugging

Start with a small, fast model to verify your environment and config work correctly before committing compute to a larger run. Recommended: Qwen/Qwen3.5-0.8B or meta-llama/Llama-3.2-1B-Instruct 
model = "Qwen/Qwen3.5-0.8B"
max_steps = 50
batch_size = 128
rollouts_per_example = 8

​
For Experimentation

MoE models with small active parameter counts give strong performance per token. Recommended: Qwen/Qwen3.5-35B-A3B 
model = "Qwen/Qwen3.5-35B-A3B"
max_steps = 200
batch_size = 256
rollouts_per_example = 16

​
For Production Training

For serious training runs where you want the strongest possible results, use the larger MoE models. Recommended: Qwen/Qwen3.5-397B-A17B or nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 
model = "Qwen/Qwen3.5-397B-A17B"
max_steps = 500
batch_size = 512
rollouts_per_example = 16

​
Thinking Mode

Qwen3.5 and Nemotron models support a thinking mode that produces extended chain-of-thought reasoning before the final answer. Toggle it via [sampling].enable_thinking in your config. Thinking mode tends to help on tasks that benefit from multi-step reasoning (math, code, logic) at the cost of longer outputs.

​
Checking Available Models

Always use the CLI to check the current list of supported models: 
prime train models
Add --output json to get the live pricing alongside the model list. This may differ from this page as models are being added regularly.