mirror of
https://github.com/tiennm99/cheahjs-free-llm-api-resources.git
synced 2026-10-13 12:14:16 +00:00
updates
This commit is contained in:
Jun Siang Cheah committed
1 parent
b760c7663e
commit
eae40dc6fb
2 files changed
+17
-44
No files matched your search
@@ -116,6 +116,8 @@ Data is used for training when used outside of the UK/CH/EEA/EU.
|
||||
<table><thead><tr><th>Model Name</th><th>Model Limits</th></tr></thead><tbody>
|
||||
<tr><td>Gemini 2.5 Pro</td><td>3,000,000 tokens/day<br>125,000 tokens/minute<br>50 requests/day<br>2 requests/minute</td></tr>
|
||||
<tr><td>Gemini 2.5 Flash</td><td>250,000 tokens/minute<br>250 requests/day<br>10 requests/minute</td></tr>
|
||||
<tr><td>Gemini 2.5 Flash-Lite</td><td>250,000 tokens/minute<br>1,000 requests/day<br>15 requests/minute</td></tr>
|
||||
<tr><td>Gemini 2.5 Flash Image Preview (Nano Banana)</td><td></td></tr>
|
||||
<tr><td>Gemini 2.0 Flash</td><td>1,000,000 tokens/minute<br>200 requests/day<br>15 requests/minute</td></tr>
|
||||
<tr><td>Gemini 2.0 Flash-Lite</td><td>1,000,000 tokens/minute<br>200 requests/day<br>30 requests/minute</td></tr>
|
||||
<tr><td>Gemini 2.0 Flash (Experimental)</td><td>250,000 tokens/minute<br>50 requests/day<br>10 requests/minute</td></tr>
|
||||
@@ -126,8 +128,6 @@ Data is used for training when used outside of the UK/CH/EEA/EU.
|
||||
<tr><td>Gemma 3 12B Instruct</td><td>15,000 tokens/minute<br>14,400 requests/day<br>30 requests/minute</td></tr>
|
||||
<tr><td>Gemma 3 4B Instruct</td><td>15,000 tokens/minute<br>14,400 requests/day<br>30 requests/minute</td></tr>
|
||||
<tr><td>Gemma 3 1B Instruct</td><td>15,000 tokens/minute<br>14,400 requests/day<br>30 requests/minute</td></tr>
|
||||
<tr><td>text-embedding-004</td><td rowspan="2">100 batch requests/minute<br>100 requests/minute<br>100 content/batch<br>Shared Quota</td></tr>
|
||||
<tr><td>embedding-001</td></tr>
|
||||
</tbody></table>
|
||||
|
||||
### [NVIDIA NIM](https://build.nvidia.com/explore/discover)
|
||||
@@ -176,6 +176,7 @@ Routes to various supported providers.
|
||||
### [Cerebras](https://cloud.cerebras.ai/)
|
||||
|
||||
<table><thead><tr><th>Model Name</th><th>Model Limits</th></tr></thead><tbody>
|
||||
<tr><td>gpt-oss-120b</td><td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td></tr>
|
||||
<tr><td>Qwen 3 235B A22B Instruct</td><td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td></tr>
|
||||
<tr><td>Qwen 3 235B A22B Thinking</td><td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td></tr>
|
||||
<tr><td>Qwen 3 Coder 480B</td><td>10 requests/minute<br>150,000 tokens/minute<br>100 requests/hour<br>1,000,000 tokens/hour<br>100 requests/day<br>1,000,000 tokens/day</td></tr>
|
||||
@@ -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)
|
||||
|
||||
|
||||
@@ -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"<tr><td>{model['name']}</td><td>{limits_str}</td></tr>\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"<tr><td>{model['name']}</td>"
|
||||
if first_embedding:
|
||||
model_list_markdown += f'<td rowspan="{len(gemini_embedding_models)}">{limits_str}<br>100 content/batch<br>Shared Quota</td>'
|
||||
first_embedding = False
|
||||
model_list_markdown += "</tr>\n"
|
||||
|
||||
model_list_markdown += "</tbody></table>\n\n"
|
||||
|
||||
# --- NVIDIA NIM ---
|
||||
@@ -815,6 +789,10 @@ def main():
|
||||
model_list_markdown += "### [Cerebras](https://cloud.cerebras.ai/)\n\n"
|
||||
model_list_markdown += "<table><thead><tr><th>Model Name</th><th>Model Limits</th></tr></thead><tbody>\n"
|
||||
cerebras_models = [
|
||||
{
|
||||
"name": "gpt-oss-120b",
|
||||
"limits_text": "30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day"
|
||||
},
|
||||
{
|
||||
"name": "Qwen 3 235B A22B Instruct",
|
||||
"limits_text": "30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>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",
|
||||
|
||||
Reference in new issue
Block a user