From f362265d12ab2c0a280090c350467d67fcc9818f Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Tue, 5 Aug 2025 09:43:01 +0100 Subject: [PATCH] update --- README.md | 35 ++++++++++++------------------ src/pull_available_models.py | 42 +++++++++++++++++++++++++++++------- 2 files changed, 48 insertions(+), 29 deletions(-) diff --git a/README.md b/README.md index 64ce9f8..b6abbe0 100644 --- a/README.md +++ b/README.md @@ -103,7 +103,6 @@ Models share a common quota. - [qwen/qwen3-coder:free](https://openrouter.ai/qwen/qwen3-coder:free) - [sarvamai/sarvam-m:free](https://openrouter.ai/sarvamai/sarvam-m:free) - [tencent/hunyuan-a13b-instruct:free](https://openrouter.ai/tencent/hunyuan-a13b-instruct:free) -- [thudm/glm-4-32b:free](https://openrouter.ai/thudm/glm-4-32b:free) - [thudm/glm-z1-32b:free](https://openrouter.ai/thudm/glm-z1-32b:free) - [tngtech/deepseek-r1t-chimera:free](https://openrouter.ai/tngtech/deepseek-r1t-chimera:free) - [tngtech/deepseek-r1t2-chimera:free](https://openrouter.ai/tngtech/deepseek-r1t2-chimera:free) @@ -175,13 +174,15 @@ Routes to various supported providers. ### [Cerebras](https://cloud.cerebras.ai/) -Free tier restricted to 8K context. - - - + + + + + - + +
Model NameModel Limits
Qwen 3 32B30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Llama 4 Scout30 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
Llama 3.3 70B30 requests/minute
64,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Qwen 3 32B30 requests/minute
64,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Llama 3.1 8B30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Llama 3.3 70B30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Llama 4 Scout30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
Llama 4 Maverick30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
### [Groq](https://console.groq.com) @@ -194,9 +195,9 @@ Free tier restricted to 8K context. Groq compound-beta200 requests/day
70,000 tokens/minute Groq compound-beta-mini200 requests/day
70,000 tokens/minute Llama 3 70B14,400 requests/day
6,000 tokens/minute -Llama 3 8B14,400 requests/day
6,000 tokens/minute -Llama 3.1 8B14,400 requests/day
6,000 tokens/minute -Llama 3.3 70B1,000 requests/day
12,000 tokens/minute +Llama 3 8B14,400 requests/day
15,000 tokens/minute +Llama 3.1 8B14,400 requests/day
20,000 tokens/minute +Llama 3.3 70B1,000 requests/day
6,000 tokens/minute Llama 4 Maverick 17B 128E Instruct1,000 requests/day
6,000 tokens/minute Llama 4 Scout Instruct1,000 requests/day
30,000 tokens/minute Whisper Large v37,200 audio-seconds/minute
2,000 requests/day @@ -302,16 +303,6 @@ Data is sent to individual hosts. **Limits:** [200 requests/day](https://x.com/rayon_labs/status/1938176081976037505). [**Requires a one time $5 top up to access the free tier.**](https://x.com/rayon_labs/status/1940416866104545608) - Various open models -- DeepCoder 14B Preview -- DeepHermes 3 Llama 3 8B Preview -- openbmb/minicpm4-8b -- qwen/qwen3-14b -- qwen/qwen3-4b -- qwen/qwen3-8b -- tencent/hunyuan-a13b-instruct -- thudm/glm-4-32b-0414 -- zai-org/glm-4.5-air -- zai-org/glm-4.5-fp8 ### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai) @@ -403,9 +394,9 @@ Very stringent payment verification for Google Cloud. **Models:** [Various open models](https://studio.nebius.ai/models) -### [Novita](https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate) +### [Novita](https://novita.ai/?ref=ytblmjc&utm_source=affiliate) -**Credits:** $0.5 for 1 year, $10 for 3 months for LLMs with [referral code](https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate) + GitHub account connection +**Credits:** $0.5 for 1 year **Models:** [Various open models](https://novita.ai/models) @@ -489,6 +480,7 @@ Very stringent payment verification for Google Cloud. - Llama-4-Maverick-17B-128E-Instruct - Qwen/Qwen3-32B - Whisper-Large-v3 +- deepseek-ai/DeepSeek-R1 - deepseek-ai/DeepSeek-R1-0528 - deepseek-ai/DeepSeek-R1-Distill-Llama-70B - deepseek-ai/DeepSeek-V3-0324 @@ -508,5 +500,6 @@ Very stringent payment verification for Google Cloud. - Pixtral 12B (2409) - Qwen2.5 Coder 32B Instruct - devstral-small-2505 +- qwen3-235b-a22b-instruct-2507 diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 3841dc2..b8fb819 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -816,14 +816,40 @@ def main(): # --- Cerebras --- model_list_markdown += "### [Cerebras](https://cloud.cerebras.ai/)\n\n" - model_list_markdown += "Free tier restricted to 8K context.\n\n" model_list_markdown += "\n" - cerebras_limit_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" cerebras_models = [ - {"name": "Qwen 3 32B", "limits_text": cerebras_limit_text}, - {"name": "Llama 4 Scout", "limits_text": cerebras_limit_text}, - {"name": "Llama 3.1 8B", "limits_text": cerebras_limit_text}, - {"name": "Llama 3.3 70B", "limits_text": cerebras_limit_text}, + { + "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" + }, + { + "name": "Qwen 3 235B A22B Thinking", + "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 Coder 480B", + "limits_text": "10 requests/minute
150,000 tokens/minute
100 requests/hour
1,000,000 tokens/hour
100 requests/day
1,000,000 tokens/day" + }, + { + "name": "Llama 3.3 70B", + "limits_text": "30 requests/minute
64,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day" + }, + { + "name": "Qwen 3 32B", + "limits_text": "30 requests/minute
64,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day" + }, + { + "name": "Llama 3.1 8B", + "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": "Llama 4 Scout", + "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": "Llama 4 Maverick", + "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" + }, ] for model in cerebras_models: model_list_markdown += ( @@ -1009,8 +1035,8 @@ def main(): }, { "name": "Novita", - "url": "https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate", - "credits": "$0.5 for 1 year, $10 for 3 months for LLMs with [referral code](https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate) + GitHub account connection", + "url": "https://novita.ai/?ref=ytblmjc&utm_source=affiliate", + "credits": "$0.5 for 1 year", "requirements": "", "models_desc": "[Various open models](https://novita.ai/models)", },
Model NameModel Limits