Models
We retain the right to change models so that we can provide models that suit your applications and our infrastructure best. You can, however, use one of the following model aliases for more reliable applications:
- alias-ha (general model, high availability)
- alias-huge (most powerful model)
- alias-code (coding support)
- alias-reasoning
- alias-image-generation (to generate images from text)
- alias-vision (to ask questions about images)
Most models also fall back to other models.
The status page lists all models and their current status.
Context Length
Here are the maximum context lengths for each chat model:
| Model name | Max tokens |
|---|---|
| google/gemma-4-31B-it | 262144 |
| meta-llama/Llama-3.1-8B-Instruct | 32768 |
| meta-llama/Llama-3.3-70B-Instruct | 40000 |
| MiniMaxAI/MiniMax-M3-MXFP8 | 524288 |
| moonshotai/Kimi-K2.7-Code | 131072 |
| openai/gpt-oss-120b | 131072 |
| openGPT-X/Teuken-7B-instruct-v0.6 | 4096 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct | 131072 |
| Qwen/Qwen3-VL-8B-Instruct | 131072 |
| zai-org/GLM-5.2-FP8 | 524288 |