Available Models
Browse LLMs available through the coding plan API, organized by plan tier.
Overview
The coding plan provides access to a curated set of LLMs for chat, code generation, and completion. Models are organized by plan tier — each tier unlocks access to the full model pool. Use the API to list currently available models.
Free plan
| Model ID | Tier | Context Window | Quantization |
|---|---|---|---|
| deepseek-v4-flash-0731 | Tier 1 | 1M tokens | FP8 |
Go plan
| Model ID | Tier | Context Window | Quantization |
|---|---|---|---|
| deepseek-v4-flash-0731 | Tier 1 | 1M tokens | FP8 |
| google/gemma-3-27b-it | Tier 1 | 128k tokens | FP8 |
| gpt-oss-20b | Tier 1 | 128k tokens | MXFP4 |
| NousResearch/Hermes-4-70B | Tier 1 | 128k tokens | FP8 |
| nvidia/Nemotron-3-Nano-Omni | Tier 1 | 128k tokens | FP8 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | Tier 1 | 128k tokens | FP8 |
| gpt-oss-120b | Tier 2 | 128k tokens | MXFP4 |
Pro plan
| Model ID | Tier | Context Window | Quantization |
|---|---|---|---|
| deepseek-v4-flash-0731 | Tier 1 | 1M tokens | FP8 |
| gpt-oss-20b | Tier 1 | 128k tokens | MXFP4 |
| NousResearch/Hermes-4-70B | Tier 1 | 128k tokens | FP8 |
| nvidia/Nemotron-3-Nano-Omni | Tier 1 | 128k tokens | FP8 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | Tier 1 | 128k tokens | FP8 |
| gpt-oss-120b | Tier 2 | 128k tokens | MXFP4 |
| deepseek-v4-pro | Tier 3 | 1M tokens | FP8 |
| glm-5.2 | Tier 3 | 1M tokens | FP8 |
| kimi-2.7 | Tier 3 | 1M tokens | FP8 |
| minmax-m3 | Tier 3 | 1M tokens | FP8 |
Model recommendations
We recommend using deepseek-v4-flash-0731 and Tier 1 models for the best balance of performance, cost, and efficiency.
Tier 2 models consume approximately 2–4× more usage than Tier 1 models.
Tier 3 models consume approximately 8–10× more usage than Tier 1 models.
To ensure the best user experience, we continuously update the models available in each tier based on performance, reliability, availability, and the latest model releases. As newer and better-performing models become available, they may be added to or replace existing models within the respective tiers.
Choosing Tier 1 models whenever possible helps maximize your available usage while maintaining excellent performance for most workloads.
Model selection
When sending a completion request, specify the model in the request body. Use "auto" to let the smart router pick the best model for your prompt.