tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-18 14:13:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

prep gemini 2.5 flash cloud next

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2025-04-08 18:37:29 +01:00
1 parent 6a6b4d819c
commit a469b8821f
2 files changed
+49 -12
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+27 -10
View File
@@ -23,7 +23,7 @@ This lists various services that provide free access or credits towards API-base
</tr>
</thead>
<tbody>
<tr><td rowspan="51"><a href="https://openrouter.ai" target="_blank">OpenRouter</a></td><td rowspan="51">20 requests/minute<br>50 requests/day</td><td>Bytedance UI Tars 72B</td><td></td></tr>
<tr><td rowspan="50"><a href="https://openrouter.ai" target="_blank">OpenRouter</a></td><td rowspan="50">20 requests/minute<br>50 requests/day</td><td>Bytedance UI Tars 72B</td><td></td></tr>
<tr><td>DeepHermes 3 Llama 3 8B Preview</td><td></td></tr>
<tr><td>DeepSeek R1</td><td></td></tr>
<tr><td>DeepSeek R1 Distill Llama 70B</td><td></td></tr>
@@ -44,10 +44,13 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Gemma 3 4B Instruct</td><td></td></tr>
<tr><td>Llama 3.1 8B Instruct</td><td></td></tr>
<tr><td>Llama 3.1 Nemotron 70B Instruct</td><td></td></tr>
<tr><td>Llama 3.1 Nemotron Nano 8B v1</td><td></td></tr>
<tr><td>Llama 3.1 Nemotron Ultra 253B v1</td><td></td></tr>
<tr><td>Llama 3.2 11B Vision Instruct</td><td></td></tr>
<tr><td>Llama 3.2 1B Instruct</td><td></td></tr>
<tr><td>Llama 3.2 3B Instruct</td><td></td></tr>
<tr><td>Llama 3.3 70B Instruct</td><td></td></tr>
<tr><td>Llama 3.3 Nemotron Super 49B v1</td><td></td></tr>
<tr><td>Llama 4 Maverick</td><td></td></tr>
<tr><td>Llama 4 Scout</td><td></td></tr>
<tr><td>Mistral 7B Instruct</td><td></td></tr>
@@ -58,9 +61,6 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Moonlight-16B-A3B-Instruct</td><td></td></tr>
<tr><td>OlympicCoder 32B</td><td></td></tr>
<tr><td>OlympicCoder 7B</td><td></td></tr>
<tr><td>OpenChat 7B</td><td></td></tr>
<tr><td>Phi-3 Medium 128k Instruct</td><td></td></tr>
<tr><td>Phi-3 Mini 128k Instruct</td><td></td></tr>
<tr><td>Qwen 2.5 72B Instruct</td><td></td></tr>
<tr><td>Qwen 2.5 7B Instruct</td><td></td></tr>
<tr><td>Qwen 2.5 VL 32B Instruct</td><td></td></tr>
@@ -72,14 +72,17 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Qwen2.5 VL 72B Instruct</td><td></td></tr>
<tr><td>Reka Flash 3</td><td></td></tr>
<tr><td>Rogue Rose 103B v0.2</td><td></td></tr>
<tr><td>Toppy M 7B</td><td></td></tr>
<tr><td>Zephyr 7B Beta</td><td></td></tr>
<tr>
<td rowspan="11"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="11">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td rowspan="14"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="14">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td>Gemini 2.5 Pro (Experimental)</td>
<td>5,000,000 tokens/day<br>1,000,000 tokens/minute<br>25 requests/day<br>5 requests/minute</td>
</tr>
<tr>
<td>Gemini 2.5 Flash (Preview)</td>
<td></td>
</tr>
<tr>
<td>Gemini 2.0 Flash</td>
<td>1,000,000 tokens/minute<br>1,500 requests/day<br>15 requests/minute</td>
@@ -112,6 +115,14 @@ This lists various services that provide free access or credits towards API-base
<td>Gemma 3 27B Instruct</td>
<td>15,000 tokens/minute<br>14,400 requests/day<br>30 requests/minute</td>
</tr>
<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>text-embedding-004</td>
<td rowspan="2">150 batch requests/minute<br>1,500 requests/minute<br>100 content/batch</td>
@@ -246,7 +257,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Phi-4</td><td></td></tr>
<tr><td>Phi-4-mini-instruct</td><td></td></tr>
<tr><td>Phi-4-multimodal-instruct</td><td></td></tr>
<tr><td rowspan="15"><a href="https://chutes.ai/" target="_blank">Chutes</a></td><td rowspan="15">Distributed, decentralized crypto-based compute. Data is sent to individual hosts.</td><td>DeepHermes 3 Llama 3 8B Preview</td><td></td></tr>
<tr><td rowspan="18"><a href="https://chutes.ai/" target="_blank">Chutes</a></td><td rowspan="18">Distributed, decentralized crypto-based compute. Data is sent to individual hosts.</td><td>DeepHermes 3 Llama 3 8B Preview</td><td></td></tr>
<tr><td>DeepSeek V3 0324</td><td></td></tr>
<tr><td>DeepSeek V3 Base</td><td></td></tr>
<tr><td>Dolphin 3.0 Mistral 24B</td><td></td></tr>
@@ -254,6 +265,9 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Gemma 3 12B Instruct</td><td></td></tr>
<tr><td>Gemma 3 1B Instruct</td><td></td></tr>
<tr><td>Gemma 3 4B Instruct</td><td></td></tr>
<tr><td>Llama 3.1 Nemotron Nano 8B v1</td><td></td></tr>
<tr><td>Llama 3.1 Nemotron Ultra 253B v1</td><td></td></tr>
<tr><td>Llama 3.3 Nemotron Super 49B v1</td><td></td></tr>
<tr><td>Llama 4 Maverick 17B 128E Instruct FP8</td><td></td></tr>
<tr><td>Llama 4 Scout 17B 16E Instruct</td><td></td></tr>
<tr><td>Mistral Small 3.1 24B Instruct 2503</td><td></td></tr>
@@ -407,7 +421,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Qwen2.5 Coder 32B Instruct</td></tr>
<tr><td>Qwen2.5 VL 72B Instruct</td></tr>
<tr><td>Qwen2.5 VL 7B Instruct</td></tr>
<tr><td rowspan="21"><a href="https://cloud.sambanova.ai/" target="_blank">SambaNova Cloud</a></td><td rowspan="21">$5 for 3 months</td><td></td><td>E5-Mistral-7B-Instruct</td></tr>
<tr><td rowspan="22"><a href="https://cloud.sambanova.ai/" target="_blank">SambaNova Cloud</a></td><td rowspan="22">$5 for 3 months</td><td></td><td>E5-Mistral-7B-Instruct</td></tr>
<tr><td></td><td>Llama 3.1 405B</td></tr>
<tr><td></td><td>Llama 3.1 70B</td></tr>
<tr><td></td><td>Llama 3.1 8B</td></tr>
@@ -416,6 +430,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td></td><td>Llama 3.2 3B</td></tr>
<tr><td></td><td>Llama 3.2 90B Vision</td></tr>
<tr><td></td><td>Llama 3.3 70B</td></tr>
<tr><td></td><td>Llama-4-Scout-17B-16E-Instruct</td></tr>
<tr><td></td><td>Llama-Guard-3-8B</td></tr>
<tr><td></td><td>Qwen/QwQ-32B</td></tr>
<tr><td></td><td>Qwen/QwQ-32B-Preview</td></tr>
@@ -428,13 +443,15 @@ This lists various services that provide free access or credits towards API-base
<tr><td></td><td>deepseek-ai/DeepSeek-V3-0324</td></tr>
<tr><td></td><td>tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3</td></tr>
<tr><td></td><td>tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3</td></tr>
<tr><td rowspan="10"><a href="https://console.scaleway.com/generative-api/models" target="_blank">Scaleway Generative APIs</a></td><td rowspan="10">1,000,000 free tokens</td><td></td><td>BGE-Multilingual-Gemma2</td></tr>
<tr><td rowspan="12"><a href="https://console.scaleway.com/generative-api/models" target="_blank">Scaleway Generative APIs</a></td><td rowspan="12">1,000,000 free tokens</td><td></td><td>BGE-Multilingual-Gemma2</td></tr>
<tr><td></td><td>DeepSeek R1 Distill Llama 70B</td></tr>
<tr><td></td><td>DeepSeek R1 Distill Llama 8B</td></tr>
<tr><td></td><td>Gemma 3 27B Instruct</td></tr>
<tr><td></td><td>Llama 3.1 70B Instruct</td></tr>
<tr><td></td><td>Llama 3.1 8B Instruct</td></tr>
<tr><td></td><td>Llama 3.3 70B Instruct</td></tr>
<tr><td></td><td>Mistral Nemo 2407</td></tr>
<tr><td></td><td>Mistral Small 3.1 24B Instruct 2503</td></tr>
<tr><td></td><td>Pixtral 12B (2409)</td></tr>
<tr><td></td><td>Qwen2.5 Coder 32B Instruct</td></tr>
<tr><td></td><td>sentence-t5-xxl</td></tr>
src/pull_available_models.py
+22 -2
View File
@@ -261,6 +261,14 @@ MODEL_TO_NAME_MAPPING = {
"nousresearch/deephermes-3-llama-3-8b-preview": "DeepHermes 3 Llama 3 8B Preview",
"chutesai/mistral-small-3.1-24b-instruct-2503": "Mistral Small 3.1 24B Instruct 2503",
"qwen/qwen2.5-vl-32b-instruct": "Qwen 2.5 VL 32B Instruct",
"nvidia/llama-3_1-nemotron-ultra-253b-v1": "Llama 3.1 Nemotron Ultra 253B v1",
"nvidia/llama-3.1-nemotron-ultra-253b-v1:free": "Llama 3.1 Nemotron Ultra 253B v1",
"nvidia/llama-3.1-nemotron-nano-8b-v1": "Llama 3.1 Nemotron Nano 8B v1",
"mistral-small-3.1-24b-instruct-2503": "Mistral Small 3.1 24B Instruct 2503",
"nvidia/llama-3_3-nemotron-super-49b-v1": "Llama 3.3 Nemotron Super 49B v1",
"gemma-3-27b-it": "Gemma 3 27B Instruct",
"nvidia/llama-3.3-nemotron-super-49b-v1:free": "Llama 3.3 Nemotron Super 49B v1",
"nvidia/llama-3.1-nemotron-nano-8b-v1:free": "Llama 3.1 Nemotron Nano 8B v1",
}
@@ -942,11 +950,15 @@ def main():
table += "</tr>\n"
table += f"""<tr>
<td rowspan="11"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="11">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td rowspan="14"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="14">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td>Gemini 2.5 Pro (Experimental)</td>
<td>{get_human_limits({"limits": gemini_models["gemini-2.0-pro-exp"]})}</td>
</tr>
<tr>
<td>Gemini 2.5 Flash (Preview)</td>
<td>{get_human_limits({"limits": gemini_models["gemini-2.5-flash-preview"]})}</td>
</tr>
<tr>
<td>Gemini 2.0 Flash</td>
<td>{get_human_limits({"limits": gemini_models["gemini-2.0-flash"]})}</td>
@@ -979,6 +991,14 @@ def main():
<td>Gemma 3 27B Instruct</td>
<td>{get_human_limits({"limits": gemini_models["gemma-3-27b"]})}</td>
</tr>
<tr>
<td>Gemma 3 12B Instruct</td>
<td>{get_human_limits({"limits": gemini_models["gemma-3-12b"]})}</td>
</tr>
<tr>
<td>Gemma 3 4B Instruct</td>
<td>{get_human_limits({"limits": gemini_models["gemma-3-4b"]})}</td>
</tr>
<tr>
<td>text-embedding-004</td>
<td rowspan="2">{get_human_limits({"limits": gemini_models["project-embedding"]})}<br>100 content/batch</td>