File size: 4,096 Bytes
cfcbbc8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
# CBORG Model Mappings - October 29, 2025

## Summary

This document shows what each `:latest` model alias maps to in the CBORG API.

## Key Findings

1. **`:latest` and base models are IDENTICAL** - Using `lbl/cborg-chat` or `lbl/cborg-chat:latest` gives you the exact same underlying model
2. You can see the actual model version by checking the `response.model` field after making a request
3. The "raw" model names show the actual provider-specific version strings

## Model Mappings

### LBL CBORG Models (Local/Custom)

| Alias | Underlying Model |
|-------|------------------|
| `lbl/cborg-chat` / `lbl/cborg-chat:latest` | `hosted_vllm/hosted_vllm/Llama-4-Scout-17B-16E-Instruct-FP8` |
| `lbl/cborg-coder` / `lbl/cborg-coder:latest` | `hosted_vllm/hosted_vllm/gpt-oss-120b` |
| `lbl/cborg-deepthought` / `lbl/cborg-deepthought:latest` | `hosted_vllm/hosted_vllm/gpt-oss-120b` |
| `lbl/cborg-mini` / `lbl/cborg-mini:latest` | `ollama/gpt-oss:20b` |
| `lbl/cborg-vision` / `lbl/cborg-vision:latest` | `hosted_vllm/hosted_vllm/Llama-4-Scout-17B-16E-Instruct-FP8` |

**Note:** `lbl/cborg-coder` and `lbl/cborg-deepthought` map to the same base model!

### Anthropic Claude Models (via AWS Bedrock)

| Alias | Underlying Model |
|-------|------------------|
| `anthropic/claude-haiku` / `anthropic/claude-haiku:latest` | `claude-haiku-4-5@20251001` |
| `anthropic/claude-opus` / `anthropic/claude-opus:latest` | `us.anthropic.claude-opus-4-1-20250805-v1:0` |
| `anthropic/claude-sonnet` / `anthropic/claude-sonnet:latest` | `claude-sonnet-4-5@20250929` |
| `anthropic/claude` / `anthropic/claude:latest` | `claude-sonnet-4-5@20250929` (same as sonnet) |
| `aws/claude-haiku` / `aws/claude-haiku:latest` | `us.anthropic.claude-haiku-4-5-20251001-v1:0` |
| `aws/claude` / `aws/claude:latest` | `us.anthropic.claude-sonnet-4-5-20250929-v1:0` |

**Version Dates:**
- Haiku: October 1, 2025
- Opus: August 5, 2025
- Sonnet: September 29, 2025

### Google Gemini Models

| Alias | Underlying Model |
|-------|------------------|
| `google/gemini` / `google/gemini:latest` | `gemini-2.5-pro` |

### OpenAI Models

| Alias | Underlying Model |
|-------|------------------|
| `openai/chatgpt:latest` | `gpt-5-2025-08-07` (August 7, 2025) |
| `openai/o:latest` | `azure/o3-2025-04-16` (April 16, 2025 via Azure) |

### xAI Grok Models

| Alias | Underlying Model |
|-------|------------------|
| `xai/grok:latest` | `grok-3` |

## How to Check Model Versions Yourself

```python
from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ['CBORG_API_KEY'],
    base_url="https://api.cborg.lbl.gov"
)

response = client.chat.completions.create(
    model="lbl/cborg-chat:latest",  # or any other model
    messages=[{"role": "user", "content": "Hi"}],
    max_tokens=5
)

print(f"Requested: lbl/cborg-chat:latest")
print(f"Actual: {response.model}")
```

## Scripts Available

1. **`list_cborg_models.py`** - List all available models (with attempted detail retrieval)
2. **`test_model_info.py`** - Test a specific model and see detailed information
   ```bash
   python test_model_info.py "lbl/cborg-chat:latest"
   ```
3. **`map_latest_models.py`** - Map all `:latest` models to their underlying versions

## Important Notes

- **The `:latest` suffix is optional** - Both `lbl/cborg-chat` and `lbl/cborg-chat:latest` are identical
- **Version information is in the response** - You must make an API call to see the underlying model
- **Some models share backends** - `lbl/cborg-coder` and `lbl/cborg-deepthought` both use `gpt-oss-120b`
- **Embedding models require different API calls** - The `nomic-embed-text` models need the embeddings API, not chat completions

## Provider-Specific Version Strings

The "raw" model names follow different conventions by provider:

- **AWS Bedrock (Anthropic)**: `us.anthropic.claude-sonnet-4-5-20250929-v1:0`
- **Google Vertex AI**: `gemini-2.5-pro`
- **Azure OpenAI**: `azure/o3-2025-04-16`
- **Native OpenAI**: `gpt-5-2025-08-07`
- **Local vLLM**: `hosted_vllm/hosted_vllm/Llama-4-Scout-17B-16E-Instruct-FP8`
- **Ollama**: `ollama/gpt-oss:20b`