# Models and Versions
## 3D Generation Models
The `model` parameter used by 3D generation endpoints such as `POST /v3/generation/text-to-model` and `POST /v3/generation/image-to-model`.
| Model ID | Description | Recommended Use Case |
| :-: | :-: | :-: |
| `v3.1-20260211` | H3.1, latest high-precision model (default) | AAA production pipelines / 3D printing & flexible manufacturing |
| `v3.0-20250812` | H3.0, previous-generation stable version | Backward compatibility |
| `v2.5-20250123` | H2.5, legacy version | Historical project compatibility |
| `P2-20260801` | P2 Preview, native quad topology; 48–50,000 triangles or 48–25,000 quads | Game characters and props / Hard-surface assets / Real-time production pipelines |
| `P1-20260311` | P1, best low-poly performance; 50–20,000 faces | Game pipelines / UGC generative gameplay / Mobile 3D assets |
## Image Generation Models
The `model` parameter used by `POST /v3/generation/text-to-image` and `POST /v3/generation/image-to-image` endpoints.
| Model ID | Characteristics |
| :-: | :-: |
| `seedream_v4` | Text-to-image default with balanced results (not supported by image-to-image) |
| `seedream_v5` | Latest version with improved quality; image-to-image default |
| `banana` | Fast generation |
| `banana_pro` | High-quality generation |
| `banana2` | Latest fast version |
| `chat_image_1` | Base image model (retiring 2026-10-23) |
| `chat_image_1.5` | Higher quality (retiring 2026-12-01) |
| `chat_image_2` | Best quality |
| `chat_image_2.5_flare` | 2.5, speed tier |
| `chat_image_2.5_sunburst` | 2.5, fidelity tier |
## Version Selection Recommendations
- **New projects**: Use the default versions — `v3.1-20260211` for 3D, `seedream_v4` for text-to-image and `seedream_v5` for image-to-image — for the best balance of quality and stability
- **Production environments**: Pin a specific model version to avoid output inconsistencies caused by model updates
- **Highest quality**: Use `v3.1-20260211` for 3D (optionally with `geometry_quality=detailed`), and choose `banana_pro` or `seedream_v5` for images depending on the scenario
- **Low-poly / game assets**: Use the P Series for 3D — cleaner topology and more precise face-count control: `P2-20260801` (Preview, native quads and a higher face budget) or `P1-20260311`
## Request Examples
```bash
# Use the default model
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-model \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a robot"}'
# Specify the flagship model
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-model \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a robot", "model": "v3.1-20260211"}'
# Generate a quad mesh with the P2 Preview
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-model \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a robot", "model": "P2-20260801", "quad": true}'
# Use an image generation model
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-image \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a futuristic city", "model": "seedream_v5"}'
```
Models and Versions
3D Generation Models
The model parameter used by 3D generation endpoints such as POST /v3/generation/text-to-model and POST /v3/generation/image-to-model.
| Model ID |
Description |
Recommended Use Case |
v3.1-20260211 |
H3.1, latest high-precision model (default) |
AAA production pipelines / 3D printing & flexible manufacturing |
v3.0-20250812 |
H3.0, previous-generation stable version |
Backward compatibility |
v2.5-20250123 |
H2.5, legacy version |
Historical project compatibility |
P2-20260801 |
P2 Preview, native quad topology; 48–50,000 triangles or 48–25,000 quads |
Game characters and props / Hard-surface assets / Real-time production pipelines |
P1-20260311 |
P1, best low-poly performance; 50–20,000 faces |
Game pipelines / UGC generative gameplay / Mobile 3D assets |
Image Generation Models
The model parameter used by POST /v3/generation/text-to-image and POST /v3/generation/image-to-image endpoints.
| Model ID |
Characteristics |
seedream_v4 |
Text-to-image default with balanced results (not supported by image-to-image) |
seedream_v5 |
Latest version with improved quality; image-to-image default |
banana |
Fast generation |
banana_pro |
High-quality generation |
banana2 |
Latest fast version |
chat_image_1 |
Base image model (retiring 2026-10-23) |
chat_image_1.5 |
Higher quality (retiring 2026-12-01) |
chat_image_2 |
Best quality |
chat_image_2.5_flare |
2.5, speed tier |
chat_image_2.5_sunburst |
2.5, fidelity tier |
Version Selection Recommendations
- New projects: Use the default versions —
v3.1-20260211 for 3D, seedream_v4 for text-to-image and seedream_v5 for image-to-image — for the best balance of quality and stability
- Production environments: Pin a specific model version to avoid output inconsistencies caused by model updates
- Highest quality: Use
v3.1-20260211 for 3D (optionally with geometry_quality=detailed), and choose banana_pro or seedream_v5 for images depending on the scenario
- Low-poly / game assets: Use the P Series for 3D — cleaner topology and more precise face-count control:
P2-20260801 (Preview, native quads and a higher face budget) or P1-20260311
Request Examples
# Use the default model
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-model \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a robot"}'
# Specify the flagship model
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-model \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a robot", "model": "v3.1-20260211"}'
# Generate a quad mesh with the P2 Preview
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-model \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a robot", "model": "P2-20260801", "quad": true}'
# Use an image generation model
curl -X POST https://openapi.tripo3d.com/v3/generation/text-to-image \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {api_key}" \
-d '{"prompt": "a futuristic city", "model": "seedream_v5"}'