tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-11 12:08:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

refac

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2025-04-13 23:04:02 +01:00
1 parent 2643ee37d5
commit bf75405597
2 files changed
+280 -227
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+76 -132
View File
@@ -23,59 +23,59 @@ This lists various services that provide free access or credits towards API-base
</tr>
</thead>
<tbody>
<tr><td rowspan="53"><a href="https://openrouter.ai" target="_blank">OpenRouter</a></td><td rowspan="53"><a href="https://openrouter.ai/docs/api-reference/limits" target="_blank">20 requests/minute<br>50 requests/day<br>1000 requests/day with $10 credit balance</a></td><td><a href='https://openrouter.ai/bytedance-research/ui-tars-72b:free' target='_blank'>Bytedance UI Tars 72B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/agentica-org/deepcoder-14b-preview:free' target='_blank'>DeepCoder 14B Preview</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/nousresearch/deephermes-3-llama-3-8b-preview:free' target='_blank'>DeepHermes 3 Llama 3 8B Preview</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1:free' target='_blank'>DeepSeek R1</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b:free' target='_blank'>DeepSeek R1 Distill Llama 70B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-distill-qwen-14b:free' target='_blank'>DeepSeek R1 Distill Qwen 14B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-distill-qwen-32b:free' target='_blank'>DeepSeek R1 Distill Qwen 32B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-zero:free' target='_blank'>DeepSeek R1 Zero</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-chat:free' target='_blank'>DeepSeek V3</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-chat-v3-0324:free' target='_blank'>DeepSeek V3 0324</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-v3-base:free' target='_blank'>DeepSeek V3 Base</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/cognitivecomputations/dolphin3.0-mistral-24b:free' target='_blank'>Dolphin 3.0 Mistral 24B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/cognitivecomputations/dolphin3.0-r1-mistral-24b:free' target='_blank'>Dolphin 3.0 R1 Mistral 24B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/featherless/qwerky-72b:free' target='_blank'>Featherless Qwerky 72B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemini-2.5-pro-exp-03-25:free' target='_blank'>Gemini 2.5 Pro Experimental 03-25</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-2-9b-it:free' target='_blank'>Gemma 2 9B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-12b-it:free' target='_blank'>Gemma 3 12B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-1b-it:free' target='_blank'>Gemma 3 1B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-27b-it:free' target='_blank'>Gemma 3 27B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-4b-it:free' target='_blank'>Gemma 3 4B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/moonshotai/kimi-vl-a3b-thinking:free' target='_blank'>Kimi VL A3B Thinking</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.1-8b-instruct:free' target='_blank'>Llama 3.1 8B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.1-nemotron-70b-instruct:free' target='_blank'>Llama 3.1 Nemotron 70B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.1-nemotron-nano-8b-v1:free' target='_blank'>Llama 3.1 Nemotron Nano 8B v1</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.1-nemotron-ultra-253b-v1:free' target='_blank'>Llama 3.1 Nemotron Ultra 253B v1</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.2-11b-vision-instruct:free' target='_blank'>Llama 3.2 11B Vision Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.2-1b-instruct:free' target='_blank'>Llama 3.2 1B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.2-3b-instruct:free' target='_blank'>Llama 3.2 3B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.3-70b-instruct:free' target='_blank'>Llama 3.3 70B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.3-nemotron-super-49b-v1:free' target='_blank'>Llama 3.3 Nemotron Super 49B v1</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-4-maverick:free' target='_blank'>Llama 4 Maverick</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-4-scout:free' target='_blank'>Llama 4 Scout</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-7b-instruct:free' target='_blank'>Mistral 7B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-nemo:free' target='_blank'>Mistral Nemo</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501:free' target='_blank'>Mistral Small 24B Instruct 2501</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-small-3.1-24b-instruct:free' target='_blank'>Mistral Small 3.1 24B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/allenai/molmo-7b-d:free' target='_blank'>Molmo 7B D</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/moonshotai/moonlight-16b-a3b-instruct:free' target='_blank'>Moonlight-16B-A3B-Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/open-r1/olympiccoder-32b:free' target='_blank'>OlympicCoder 32B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/open-r1/olympiccoder-7b:free' target='_blank'>OlympicCoder 7B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/arliai/qwq-32b-arliai-rpr-v1:free' target='_blank'>QwQ 32B ArliAI RpR v1</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-72b-instruct:free' target='_blank'>Qwen 2.5 72B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-7b-instruct:free' target='_blank'>Qwen 2.5 7B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen2.5-vl-32b-instruct:free' target='_blank'>Qwen 2.5 VL 32B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen2.5-vl-3b-instruct:free' target='_blank'>Qwen 2.5 VL 3B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-vl-7b-instruct:free' target='_blank'>Qwen 2.5 VL 7B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwq-32b:free' target='_blank'>Qwen QwQ 32B</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwq-32b-preview:free' target='_blank'>Qwen QwQ 32B Preview</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct:free' target='_blank'>Qwen2.5 Coder 32B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct:free' target='_blank'>Qwen2.5 VL 72B Instruct</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/rekaai/reka-flash-3:free' target='_blank'>Reka Flash 3</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/sophosympatheia/rogue-rose-103b-v0.2:free' target='_blank'>Rogue Rose 103B v0.2</a></td><td></td></tr>
<tr><td><a href='https://openrouter.ai/huggingfaceh4/zephyr-7b-beta:free' target='_blank'>Zephyr 7B Beta</a></td><td></td></tr>
<tr><td rowspan="53"><a href="https://openrouter.ai" target="_blank">OpenRouter</a></td><td rowspan="53"><a href="https://openrouter.ai/docs/api-reference/limits" target="_blank">20 requests/minute<br>50 requests/day<br>1000 requests/day with $10 credit balance</a></td><td><a href='https://openrouter.ai/bytedance-research/ui-tars-72b:free' target='_blank'>Bytedance UI Tars 72B</a></td><td rowspan="53">Shared Quota</td></tr>
<tr><td><a href='https://openrouter.ai/agentica-org/deepcoder-14b-preview:free' target='_blank'>DeepCoder 14B Preview</a></td></tr>
<tr><td><a href='https://openrouter.ai/nousresearch/deephermes-3-llama-3-8b-preview:free' target='_blank'>DeepHermes 3 Llama 3 8B Preview</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1:free' target='_blank'>DeepSeek R1</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b:free' target='_blank'>DeepSeek R1 Distill Llama 70B</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-distill-qwen-14b:free' target='_blank'>DeepSeek R1 Distill Qwen 14B</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-distill-qwen-32b:free' target='_blank'>DeepSeek R1 Distill Qwen 32B</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-r1-zero:free' target='_blank'>DeepSeek R1 Zero</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-chat:free' target='_blank'>DeepSeek V3</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-chat-v3-0324:free' target='_blank'>DeepSeek V3 0324</a></td></tr>
<tr><td><a href='https://openrouter.ai/deepseek/deepseek-v3-base:free' target='_blank'>DeepSeek V3 Base</a></td></tr>
<tr><td><a href='https://openrouter.ai/cognitivecomputations/dolphin3.0-mistral-24b:free' target='_blank'>Dolphin 3.0 Mistral 24B</a></td></tr>
<tr><td><a href='https://openrouter.ai/cognitivecomputations/dolphin3.0-r1-mistral-24b:free' target='_blank'>Dolphin 3.0 R1 Mistral 24B</a></td></tr>
<tr><td><a href='https://openrouter.ai/featherless/qwerky-72b:free' target='_blank'>Featherless Qwerky 72B</a></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemini-2.5-pro-exp-03-25:free' target='_blank'>Gemini 2.5 Pro Experimental 03-25</a></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-2-9b-it:free' target='_blank'>Gemma 2 9B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-12b-it:free' target='_blank'>Gemma 3 12B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-1b-it:free' target='_blank'>Gemma 3 1B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-27b-it:free' target='_blank'>Gemma 3 27B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/google/gemma-3-4b-it:free' target='_blank'>Gemma 3 4B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/moonshotai/kimi-vl-a3b-thinking:free' target='_blank'>Kimi VL A3B Thinking</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.1-8b-instruct:free' target='_blank'>Llama 3.1 8B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.1-nemotron-70b-instruct:free' target='_blank'>Llama 3.1 Nemotron 70B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.1-nemotron-nano-8b-v1:free' target='_blank'>Llama 3.1 Nemotron Nano 8B v1</a></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.1-nemotron-ultra-253b-v1:free' target='_blank'>Llama 3.1 Nemotron Ultra 253B v1</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.2-11b-vision-instruct:free' target='_blank'>Llama 3.2 11B Vision Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.2-1b-instruct:free' target='_blank'>Llama 3.2 1B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.2-3b-instruct:free' target='_blank'>Llama 3.2 3B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-3.3-70b-instruct:free' target='_blank'>Llama 3.3 70B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/nvidia/llama-3.3-nemotron-super-49b-v1:free' target='_blank'>Llama 3.3 Nemotron Super 49B v1</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-4-maverick:free' target='_blank'>Llama 4 Maverick</a></td></tr>
<tr><td><a href='https://openrouter.ai/meta-llama/llama-4-scout:free' target='_blank'>Llama 4 Scout</a></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-7b-instruct:free' target='_blank'>Mistral 7B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-nemo:free' target='_blank'>Mistral Nemo</a></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501:free' target='_blank'>Mistral Small 24B Instruct 2501</a></td></tr>
<tr><td><a href='https://openrouter.ai/mistralai/mistral-small-3.1-24b-instruct:free' target='_blank'>Mistral Small 3.1 24B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/allenai/molmo-7b-d:free' target='_blank'>Molmo 7B D</a></td></tr>
<tr><td><a href='https://openrouter.ai/moonshotai/moonlight-16b-a3b-instruct:free' target='_blank'>Moonlight-16B-A3B-Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/open-r1/olympiccoder-32b:free' target='_blank'>OlympicCoder 32B</a></td></tr>
<tr><td><a href='https://openrouter.ai/open-r1/olympiccoder-7b:free' target='_blank'>OlympicCoder 7B</a></td></tr>
<tr><td><a href='https://openrouter.ai/arliai/qwq-32b-arliai-rpr-v1:free' target='_blank'>QwQ 32B ArliAI RpR v1</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-72b-instruct:free' target='_blank'>Qwen 2.5 72B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-7b-instruct:free' target='_blank'>Qwen 2.5 7B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen2.5-vl-32b-instruct:free' target='_blank'>Qwen 2.5 VL 32B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen2.5-vl-3b-instruct:free' target='_blank'>Qwen 2.5 VL 3B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-vl-7b-instruct:free' target='_blank'>Qwen 2.5 VL 7B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwq-32b:free' target='_blank'>Qwen QwQ 32B</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwq-32b-preview:free' target='_blank'>Qwen QwQ 32B Preview</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct:free' target='_blank'>Qwen2.5 Coder 32B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct:free' target='_blank'>Qwen2.5 VL 72B Instruct</a></td></tr>
<tr><td><a href='https://openrouter.ai/rekaai/reka-flash-3:free' target='_blank'>Reka Flash 3</a></td></tr>
<tr><td><a href='https://openrouter.ai/sophosympatheia/rogue-rose-103b-v0.2:free' target='_blank'>Rogue Rose 103B v0.2</a></td></tr>
<tr><td><a href='https://openrouter.ai/huggingfaceh4/zephyr-7b-beta:free' target='_blank'>Zephyr 7B Beta</a></td></tr>
<tr><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 2.0 Flash</td><td>1,000,000 tokens/minute<br>1,500 requests/day<br>15 requests/minute</td></tr>
<tr><td>Gemini 2.0 Flash-Lite</td><td>1,000,000 tokens/minute<br>1,500 requests/day<br>30 requests/minute</td></tr>
@@ -157,46 +157,18 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Mixtral 8x7B Instruct v0.1</td><td>12 requests/minute</td></tr>
<tr><td>Qwen 2.5 VL 72B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Qwen2.5 Coder 32B Instruct</td><td>12 requests/minute</td></tr>
<tr>
<td rowspan="3"><a href="https://together.ai">Together</a></td>
<td rowspan="3"></td>
<td><a href="https://www.together.ai/models/llama-3-2-11b-free" target="_blank">Llama 3.2 11B Vision Instruct</a></td>
<td></td>
</tr>
<tr>
<td><a href="https://www.together.ai/models/llama-3-3-70b-free" target="_blank">Llama 3.3 70B Instruct</a></td>
<td></td>
</tr>
<tr>
<td><a href="https://www.together.ai/models/deepseek-r1-distilled-llama-70b-free" target="_blank">DeepSeek R1 Distil Llama 70B</a></td>
<td></td>
</tr><tr>
<td rowspan="8"><a href="https://cohere.com" target="_blank">Cohere</a></td>
<td rowspan="8"><a href="https://docs.cohere.com/docs/rate-limits">20 requests/minute<br>1,000 requests/month</a></td>
<td>Command-R</td>
<td rowspan="8">Shared Limit</td>
</tr>
<tr>
<td>Command-R+</td>
</tr>
<tr>
<td>Command-R7B</td>
</tr>
<tr>
<td>Command-A</td>
</tr>
<tr>
<td>Aya Expanse 8B</td>
</tr>
<tr>
<td>Aya Expanse 32B</td>
</tr>
<tr>
<td>Aya Vision 8B</td>
</tr>
<tr>
<td>Aya Vision 32B</td>
</tr><tr><td rowspan="49"><a href="https://github.com/marketplace/models" target="_blank">GitHub Models</a></td><td rowspan="49">Extremely restrictive input/output token limits.<br><a href="https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits" target="_blank">Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)</a></td><td>AI21 Jamba 1.5 Large</td><td></td></tr>
<tr><td rowspan="3"><a href="https://together.ai" target="_blank">Together</a></td><td rowspan="3">Up to 60 requests/minute</td><td><a href='https://together.ai/llama-3-2-11b-free' target='_blank'>Llama 3.2 11B Vision Instruct</a></td><td></td></tr>
<tr><td><a href='https://together.ai/llama-3-3-70b-free' target='_blank'>Llama 3.3 70B Instruct</a></td><td></td></tr>
<tr><td><a href='https://together.ai/deepseek-r1-distilled-llama-70b-free' target='_blank'>DeepSeek R1 Distil Llama 70B</a></td><td></td></tr>
<tr><td rowspan="8"><a href="https://cohere.com" target="_blank">Cohere</a></td><td rowspan="8"><a href="https://docs.cohere.com/docs/rate-limits">20 requests/minute<br>1,000 requests/month</a></td><td>Command-A</td><td rowspan="{len(cohere_models)}">Shared Limit</td></tr>
<tr><td>Command-R7B</td></tr>
<tr><td>Command-R+</td></tr>
<tr><td>Command-R</td></tr>
<tr><td>Aya Expanse 8B</td></tr>
<tr><td>Aya Expanse 32B</td></tr>
<tr><td>Aya Vision 8B</td></tr>
<tr><td>Aya Vision 32B</td></tr>
<tr><td rowspan="49"><a href="https://github.com/marketplace/models" target="_blank">GitHub Models</a></td><td rowspan="49">Extremely restrictive input/output token limits.<br><a href="https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits" target="_blank">Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)</a></td><td>AI21 Jamba 1.5 Large</td><td></td></tr>
<tr><td>AI21 Jamba 1.5 Mini</td><td></td></tr>
<tr><td>Codestral 25.01</td><td></td></tr>
<tr><td>Cohere Command R</td><td></td></tr>
@@ -317,45 +289,17 @@ This lists various services that provide free access or credits towards API-base
<tr><td>TinyLlama 1.1B Chat v1.0</td><td></td></tr>
<tr><td>Una Cybertron 7B v2 (BF16)</td><td></td></tr>
<tr><td>Zephyr 7B Beta (AWQ)</td><td></td></tr>
<tr>
<td rowspan="10"><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td rowspan="10">Very stringent payment verification for Google Cloud.</td>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-4-maverick-17b-128e-instruct-maas" target="_blank">Llama 4 Maverick Instruct</a></td>
<td>Llama 4 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-4-scout-70b-instruct-maas" target="_blank">Llama 4 Scout Instruct</a></td>
<td>Llama 4 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.1-405b-instruct-maas" target="_blank">Llama 3.1 70B Instruct</a></td>
<td>Llama 3.1 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.1-405b-instruct-maas" target="_blank">Llama 3.1 8B Instruct</a></td>
<td>Llama 3.1 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" target="_blank">Llama 3.2 90B Vision Instruct</a></td>
<td>Llama 3.2 API Service free during preview.<br>30 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.3-70b-instruct-maas" target="_blank">Llama 3.3 70B Instruct</a></td>
<td>Llama 3.3 API Service free during preview.<br>30 requests/minute</td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.5 Pro Experimental</a></td>
<td rowspan="4">Experimental Gemini model.<br>10 requests/minute</td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Flash Experimental</a></td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Flash Thinking Experimental</a></td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Pro Experimental</a></td>
</tr></tbody></table>
<tr><td rowspan="10"><a href="https://console.cloud.google.com/vertex-ai/model-garden" target="_blank">Google Cloud Vertex AI</a></td><td rowspan="10">Very stringent payment verification for Google Cloud.</td><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.5 Pro (Experimental)</a></td><td rowspan='4'>10 requests/minute<br>Shared Quota</td></tr>
<tr><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Flash (Experimental)</a></td></tr>
<tr><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Flash Thinking (Experimental)</a></td></tr>
<tr><td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Pro (Experimental)</a></td></tr>
<tr><td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-4-maverick-17b-128e-instruct-maas' target='_blank'>Llama 4 Maverick Instruct</a></td><td>60 requests/minute<br>Free during preview</td></tr>
<tr><td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-4-maverick-17b-128e-instruct-maas' target='_blank'>Llama 4 Scout Instruct</a></td><td>60 requests/minute<br>Free during preview</td></tr>
<tr><td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-3-70b-instruct-maas' target='_blank'>Llama 3.3 70B Instruct</a></td><td>30 requests/minute<br>Free during preview</td></tr>
<tr><td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-2-90b-vision-instruct-maas' target='_blank'>Llama 3.2 90B Vision Instruct</a></td><td>30 requests/minute<br>Free during preview</td></tr>
<tr><td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-1-405b-instruct-maas' target='_blank'>Llama 3.1 70B Instruct</a></td><td>60 requests/minute<br>Free during preview</td></tr>
<tr><td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-1-405b-instruct-maas' target='_blank'>Llama 3.1 8B Instruct</a></td><td>60 requests/minute<br>Free during preview</td></tr>
</tbody></table>
## Providers with trial credits
src/pull_available_models.py
+204 -95
View File
@@ -581,26 +581,83 @@ def main():
table += f'<td rowspan="{len(openrouter_models)}"><a href="https://openrouter.ai/docs/api-reference/limits" target="_blank">{get_human_limits(model)}<br>1000 requests/day with $10 credit balance</a></td>'
table += f"<td><a href='https://openrouter.ai/{model['id']}' target='_blank'>{model['name']}</a></td>"
table += "<td></td>"
if idx == 0:
table += f'<td rowspan="{len(openrouter_models)}">Shared Quota</td>'
table += "</tr>\n"
gemini_text_models = [
{"id": "gemini-2.5-pro-exp-03-25", "name": "Gemini 2.5 Pro (Experimental)", "limits": gemini_models["gemini-2.0-pro-exp"]},
{"id": "gemini-2.0-flash", "name": "Gemini 2.0 Flash", "limits": gemini_models["gemini-2.0-flash"]},
{"id": "gemini-2.0-flash-lite", "name": "Gemini 2.0 Flash-Lite", "limits": gemini_models["gemini-2.0-flash-lite"]},
{"id": "gemini-2.0-flash-exp", "name": "Gemini 2.0 Flash (Experimental)", "limits": gemini_models["gemini-2.0-flash-exp"]},
{"id": "gemini-1.5-flash", "name": "Gemini 1.5 Flash", "limits": gemini_models["gemini-1.5-flash"]},
{"id": "gemini-1.5-flash-8b", "name": "Gemini 1.5 Flash-8B", "limits": gemini_models["gemini-1.5-flash-8b"]},
{"id": "gemini-1.5-pro", "name": "Gemini 1.5 Pro", "limits": gemini_models["gemini-1.5-pro"]},
{"id": "learnlm-1.5-pro-experimental", "name": "LearnLM 1.5 Pro (Experimental)", "limits": gemini_models["learnlm-1.5-pro-experimental"]},
{"id": "gemma-3-27b-it", "name": "Gemma 3 27B Instruct", "limits": gemini_models["gemma-3-27b"]},
{"id": "gemma-3-12b-it", "name": "Gemma 3 12B Instruct", "limits": gemini_models["gemma-3-12b"]},
{"id": "gemma-3-4b-it", "name": "Gemma 3 4B Instruct", "limits": gemini_models["gemma-3-4b"]},
{"id": "gemma-3-1b-it", "name": "Gemma 3 1B Instruct", "limits": gemini_models["gemma-3-1b"]},
{
"id": "gemini-2.5-pro-exp-03-25",
"name": "Gemini 2.5 Pro (Experimental)",
"limits": gemini_models["gemini-2.0-pro-exp"],
},
{
"id": "gemini-2.0-flash",
"name": "Gemini 2.0 Flash",
"limits": gemini_models["gemini-2.0-flash"],
},
{
"id": "gemini-2.0-flash-lite",
"name": "Gemini 2.0 Flash-Lite",
"limits": gemini_models["gemini-2.0-flash-lite"],
},
{
"id": "gemini-2.0-flash-exp",
"name": "Gemini 2.0 Flash (Experimental)",
"limits": gemini_models["gemini-2.0-flash-exp"],
},
{
"id": "gemini-1.5-flash",
"name": "Gemini 1.5 Flash",
"limits": gemini_models["gemini-1.5-flash"],
},
{
"id": "gemini-1.5-flash-8b",
"name": "Gemini 1.5 Flash-8B",
"limits": gemini_models["gemini-1.5-flash-8b"],
},
{
"id": "gemini-1.5-pro",
"name": "Gemini 1.5 Pro",
"limits": gemini_models["gemini-1.5-pro"],
},
{
"id": "learnlm-1.5-pro-experimental",
"name": "LearnLM 1.5 Pro (Experimental)",
"limits": gemini_models["learnlm-1.5-pro-experimental"],
},
{
"id": "gemma-3-27b-it",
"name": "Gemma 3 27B Instruct",
"limits": gemini_models["gemma-3-27b"],
},
{
"id": "gemma-3-12b-it",
"name": "Gemma 3 12B Instruct",
"limits": gemini_models["gemma-3-12b"],
},
{
"id": "gemma-3-4b-it",
"name": "Gemma 3 4B Instruct",
"limits": gemini_models["gemma-3-4b"],
},
{
"id": "gemma-3-1b-it",
"name": "Gemma 3 1B Instruct",
"limits": gemini_models["gemma-3-1b"],
},
]
gemini_embedding_models = [
{"id": "text-embedding-004", "name": "text-embedding-004", "limits": gemini_models["project-embedding"]},
{"id": "embedding-001", "name": "embedding-001", "limits": gemini_models["project-embedding"]},
{
"id": "text-embedding-004",
"name": "text-embedding-004",
"limits": gemini_models["project-embedding"],
},
{
"id": "embedding-001",
"name": "embedding-001",
"limits": gemini_models["project-embedding"],
},
]
for idx, model in enumerate(gemini_text_models):
@@ -688,48 +745,59 @@ def main():
table += f"<td>{get_human_limits(model)}</td>"
table += "</tr>\n"
table += """<tr>
<td rowspan="3"><a href="https://together.ai">Together</a></td>
<td rowspan="3"></td>
<td><a href="https://www.together.ai/models/llama-3-2-11b-free" target="_blank">Llama 3.2 11B Vision Instruct</a></td>
<td></td>
</tr>
<tr>
<td><a href="https://www.together.ai/models/llama-3-3-70b-free" target="_blank">Llama 3.3 70B Instruct</a></td>
<td></td>
</tr>
<tr>
<td><a href="https://www.together.ai/models/deepseek-r1-distilled-llama-70b-free" target="_blank">DeepSeek R1 Distil Llama 70B</a></td>
<td></td>
</tr>"""
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",
"urlId": "llama-3-3-70b-free",
},
{
"id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free",
"name": "DeepSeek R1 Distil Llama 70B",
"urlId": "deepseek-r1-distilled-llama-70b-free",
},
]
table += """<tr>
<td rowspan="8"><a href="https://cohere.com" target="_blank">Cohere</a></td>
<td rowspan="8"><a href="https://docs.cohere.com/docs/rate-limits">20 requests/minute<br>1,000 requests/month</a></td>
<td>Command-R</td>
<td rowspan="8">Shared Limit</td>
</tr>
<tr>
<td>Command-R+</td>
</tr>
<tr>
<td>Command-R7B</td>
</tr>
<tr>
<td>Command-A</td>
</tr>
<tr>
<td>Aya Expanse 8B</td>
</tr>
<tr>
<td>Aya Expanse 32B</td>
</tr>
<tr>
<td>Aya Vision 8B</td>
</tr>
<tr>
<td>Aya Vision 32B</td>
</tr>"""
for idx, model in enumerate(together_models):
table += "<tr>"
if idx == 0:
table += f'<td rowspan="{len(together_models)}">'
table += '<a href="https://together.ai" target="_blank">Together</a>'
table += "</td>"
table += (
f'<td rowspan="{len(together_models)}">Up to 60 requests/minute</td>'
)
table += f"<td><a href='https://together.ai/{model['urlId']}' target='_blank'>{model['name']}</a></td>"
table += f"<td>{get_human_limits(model)}</td>"
table += "</tr>\n"
cohere_models = [
{"id": "command-a-03-2025", "name": "Command-A"},
{"id": "command-r7b-12-2024", "name": "Command-R7B"},
{"id": "command-r-plus", "name": "Command-R+"},
{"id": "command-r", "name": "Command-R"},
{"id": "c4ai-aya-expanse-8b", "name": "Aya Expanse 8B"},
{"id": "c4ai-aya-expanse-32b", "name": "Aya Expanse 32B"},
{"id": "c4ai-aya-vision-8b", "name": "Aya Vision 8B"},
{"id": "c4ai-aya-vision-32b", "name": "Aya Vision 32B"},
]
for idx, model in enumerate(cohere_models):
table += "<tr>"
if idx == 0:
table += f'<td rowspan="{len(cohere_models)}">'
table += '<a href="https://cohere.com" target="_blank">Cohere</a>'
table += "</td>"
table += f'<td rowspan="{len(cohere_models)}"><a href="https://docs.cohere.com/docs/rate-limits">20 requests/minute<br>1,000 requests/month</a></td>'
table += f"<td>{model['name']}</td>"
if idx == 0:
table += '<td rowspan="{len(cohere_models)}">Shared Limit</td>'
table += "</tr>\n"
for idx, model in enumerate(github_models):
table += "<tr>"
@@ -775,45 +843,86 @@ def main():
table += "<td></td>"
table += "</tr>\n"
table += """<tr>
<td rowspan="10"><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td rowspan="10">Very stringent payment verification for Google Cloud.</td>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-4-maverick-17b-128e-instruct-maas" target="_blank">Llama 4 Maverick Instruct</a></td>
<td>Llama 4 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-4-scout-70b-instruct-maas" target="_blank">Llama 4 Scout Instruct</a></td>
<td>Llama 4 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.1-405b-instruct-maas" target="_blank">Llama 3.1 70B Instruct</a></td>
<td>Llama 3.1 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.1-405b-instruct-maas" target="_blank">Llama 3.1 8B Instruct</a></td>
<td>Llama 3.1 API Service free during preview.<br>60 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" target="_blank">Llama 3.2 90B Vision Instruct</a></td>
<td>Llama 3.2 API Service free during preview.<br>30 requests/minute</td>
</tr>
<tr>
<td><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.3-70b-instruct-maas" target="_blank">Llama 3.3 70B Instruct</a></td>
<td>Llama 3.3 API Service free during preview.<br>30 requests/minute</td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.5 Pro Experimental</a></td>
<td rowspan="4">Experimental Gemini model.<br>10 requests/minute</td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Flash Experimental</a></td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Flash Thinking Experimental</a></td>
</tr>
<tr>
<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">Gemini 2.0 Pro Experimental</a></td>
</tr>"""
vertex_llama_models = [
{
"id": "llama-4-maverick-17b-128e-instruct-maas",
"name": "Llama 4 Maverick Instruct",
"urlId": "llama-4-maverick-17b-128e-instruct-maas",
"limits": {"requests/minute": 60},
},
{
"id": "llama-4-scout-17b-16e-instruct-maas",
"name": "Llama 4 Scout Instruct",
"urlId": "llama-4-maverick-17b-128e-instruct-maas",
"limits": {"requests/minute": 60},
},
{
"id": "llama-3.3-70b-instruct-maas",
"name": "Llama 3.3 70B Instruct",
"urlId": "llama-3-3-70b-instruct-maas",
"limits": {"requests/minute": 30},
},
{
"id": "llama-3.2-90b-vision-instruct-maas",
"name": "Llama 3.2 90B Vision Instruct",
"urlId": "llama-3-2-90b-vision-instruct-maas",
"limits": {"requests/minute": 30},
},
{
"id": "llama-3.1-70b-instruct-maas",
"name": "Llama 3.1 70B Instruct",
"urlId": "llama-3-1-405b-instruct-maas",
"limits": {"requests/minute": 60},
},
{
"id": "llama-3.1-8b-instruct-maas",
"name": "Llama 3.1 8B Instruct",
"urlId": "llama-3-1-405b-instruct-maas",
"limits": {"requests/minute": 60},
},
]
vertex_gemini_models = [
{
"id": "gemini-2.5-pro-exp-03-25",
"name": "Gemini 2.5 Pro (Experimental)",
"limits": {"requests/minute": 10},
},
{
"id": "gemini-2.0-flash-exp",
"name": "Gemini 2.0 Flash (Experimental)",
"limits": {"requests/minute": 10},
},
{
"id": "gemini-2.0-flash-thinking-exp-01-21",
"name": "Gemini 2.0 Flash Thinking (Experimental)",
"limits": {"requests/minute": 10},
},
{
"id": "gemini-exp-1206",
"name": "Gemini 2.0 Pro (Experimental)",
"limits": {"requests/minute": 10},
},
]
for idx, model in enumerate(vertex_gemini_models):
table += "<tr>"
if idx == 0:
table += (
f'<td rowspan="{len(vertex_llama_models) + len(vertex_gemini_models)}">'
)
table += '<a href="https://console.cloud.google.com/vertex-ai/model-garden" target="_blank">Google Cloud Vertex AI</a>'
table += "</td>"
table += f'<td rowspan="{len(vertex_llama_models) + len(vertex_gemini_models)}">Very stringent payment verification for Google Cloud.</td>'
table += f'<td><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental" target="_blank">{model['name']}</a></td>'
if idx == 0:
table += f"<td rowspan='{len(vertex_gemini_models)}'>{get_human_limits(model)}<br>Shared Quota</td>"
table += "</tr>\n"
for idx, model in enumerate(vertex_llama_models):
table += "<tr>"
table += f"<td><a href='https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/{model['urlId']}' target='_blank'>{model['name']}</a></td>"
table += f"<td>{get_human_limits(model)}<br>Free during preview</td>"
table += "</tr>\n"
table += "</tbody></table>"