From eae40dc6fb7e4d0dadffd78727c82ae3c72da889 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Sat, 6 Sep 2025 18:05:09 +0100 Subject: [PATCH] updates --- README.md | 6 ++-- src/pull_available_models.py | 55 +++++++++--------------------------- 2 files changed, 17 insertions(+), 44 deletions(-) diff --git a/README.md b/README.md index f6002df..8552d06 100644 --- a/README.md +++ b/README.md @@ -116,6 +116,8 @@ Data is used for training when used outside of the UK/CH/EEA/EU. + + @@ -126,8 +128,6 @@ Data is used for training when used outside of the UK/CH/EEA/EU. - -
Model NameModel Limits
Gemini 2.5 Pro3,000,000 tokens/day
125,000 tokens/minute
50 requests/day
2 requests/minute
Gemini 2.5 Flash250,000 tokens/minute
250 requests/day
10 requests/minute
Gemini 2.5 Flash-Lite250,000 tokens/minute
1,000 requests/day
15 requests/minute
Gemini 2.5 Flash Image Preview (Nano Banana)
Gemini 2.0 Flash1,000,000 tokens/minute
200 requests/day
15 requests/minute
Gemini 2.0 Flash-Lite1,000,000 tokens/minute
200 requests/day
30 requests/minute
Gemini 2.0 Flash (Experimental)250,000 tokens/minute
50 requests/day
10 requests/minute
Gemma 3 12B Instruct15,000 tokens/minute
14,400 requests/day
30 requests/minute
Gemma 3 4B Instruct15,000 tokens/minute
14,400 requests/day
30 requests/minute
Gemma 3 1B Instruct15,000 tokens/minute
14,400 requests/day
30 requests/minute
text-embedding-004100 batch requests/minute
100 requests/minute
100 content/batch
Shared Quota
embedding-001
### [NVIDIA NIM](https://build.nvidia.com/explore/discover) @@ -176,6 +176,7 @@ Routes to various supported providers. ### [Cerebras](https://cloud.cerebras.ai/) + @@ -214,7 +215,6 @@ Routes to various supported providers. **Limits:** Up to 60 requests/minute -- [Llama 3.2 11B Vision Instruct](https://together.ai/models/llama-3-2-11b-free) - [Llama 3.3 70B Instruct](https://together.ai/models/llama-3-3-70b-free) - [DeepSeek R1 Distil Llama 70B](https://together.ai/models/deepseek-r1-distilled-llama-70b-free) diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 9fc41bc..40f6730 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -449,19 +449,6 @@ def fetch_gemini_limits(logger): models[dimension.dimensions.get("model")][ f"requests/{quota.refresh_interval}" ] = dimension.details.value - elif quota.metric == "generativelanguage.googleapis.com/embed_text_requests": - for dimension in quota.dimensions_infos: - models["project-embedding"][f"requests/{quota.refresh_interval}"] = ( - dimension.details.value - ) - elif ( - quota.metric - == "generativelanguage.googleapis.com/batch_embed_text_requests" - ): - for dimension in quota.dimensions_infos: - models["project-embedding"][ - f"batch requests/{quota.refresh_interval}" - ] = dimension.details.value logger.debug(json.dumps(models, indent=4)) return models @@ -611,7 +598,6 @@ def main(): hyperbolic_logger = create_logger("Hyperbolic") samba_logger = create_logger("SambaNova") scaleway_logger = create_logger("Scaleway") - chutes_logger = create_logger("Chutes") fetch_concurrently = os.getenv("FETCH_CONCURRENTLY", "false").lower() == "true" @@ -682,6 +668,16 @@ def main(): "name": "Gemini 2.5 Flash", "limits": gemini_models.get("gemini-2.5-flash", {}), }, + { + "id": "gemini-2.5-flash-lite", + "name": "Gemini 2.5 Flash-Lite", + "limits": gemini_models.get("gemini-2.5-flash-lite", {}), + }, + { + "id": "gemini-2.5-flash-image-preview", + "name": "Gemini 2.5 Flash Image Preview (Nano Banana)", + "limits": gemini_models.get("gemini-2.5-flash-image-preview", {}), + }, { "id": "gemini-2.0-flash", "name": "Gemini 2.0 Flash", @@ -733,18 +729,6 @@ def main(): "limits": gemini_models.get("gemma-3-1b", {}), }, ] - gemini_embedding_models = [ - { - "id": "text-embedding-004", - "name": "text-embedding-004", - "limits": gemini_models.get("project-embedding", {}), - }, - { - "id": "embedding-001", - "name": "embedding-001", - "limits": gemini_models.get("project-embedding", {}), - }, - ] # Write text models to table for model in gemini_text_models: @@ -753,16 +737,6 @@ def main(): f"\n" ) - # Write embedding models to table - first_embedding = True - for model in gemini_embedding_models: - limits_str = get_human_limits(model) - model_list_markdown += f"" - if first_embedding: - model_list_markdown += f'' - first_embedding = False - model_list_markdown += "\n" - model_list_markdown += "
Model NameModel Limits
gpt-oss-120b30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Qwen 3 235B A22B Instruct30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Qwen 3 235B A22B Thinking30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Qwen 3 Coder 480B10 requests/minute
150,000 tokens/minute
100 requests/hour
1,000,000 tokens/hour
100 requests/day
1,000,000 tokens/day
{model['name']}{limits_str}
{model['name']}{limits_str}
100 content/batch
Shared Quota
\n\n" # --- NVIDIA NIM --- @@ -815,6 +789,10 @@ def main(): model_list_markdown += "### [Cerebras](https://cloud.cerebras.ai/)\n\n" model_list_markdown += "\n" cerebras_models = [ + { + "name": "gpt-oss-120b", + "limits_text": "30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day" + }, { "name": "Qwen 3 235B A22B Instruct", "limits_text": "30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day" @@ -868,11 +846,6 @@ def main(): # --- Together --- together_models = [ - { - "id": "meta-llama/Llama-Vision-Free", - "name": "Llama 3.2 11B Vision Instruct", - "urlId": "llama-3-2-11b-free", - }, { "id": "llmeta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "name": "Llama 3.3 70B Instruct",
Model NameModel Limits