update

2026-10-11 03:13:06 +00:00 · 2025-06-27 10:11:45 +01:00
1 parent 07b8d6fda5
commit f75f60bbcd
@@ -18,6 +18,7 @@ This lists various services that provide free access or credits towards API-base
  - [Mistral (La Plateforme)](#mistral-la-plateforme)
  - [Mistral (Codestral)](#mistral-codestral)
  - [HuggingFace Inference Providers](#huggingface-inference-providers)
+  - [Vercel AI Gateway](#vercel-ai-gateway)
  - [Cerebras](#cerebras)
  - [Groq](#groq)
  - [Together (Free)](#together-free)
@@ -39,7 +40,6 @@ This lists various services that provide free access or credits towards API-base
  - [Alibaba Cloud (International) Model Studio](#alibaba-cloud-international-model-studio)
  - [Modal](#modal)
  - [Inference.net](#inferencenet)
-  - [CentML](#centml)
  - [nCompass](#ncompass)
  - [Kluster](#kluster)
  - [Hyperbolic](#hyperbolic)
@@ -114,7 +114,7 @@ Models share a common quota.
 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 Flash (Preview)</td><td>250,000 tokens/minute<br>250 requests/day<br>10 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 2.0 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>
@@ -165,6 +165,13 @@ HuggingFace Serverless Inference limited to models smaller than 10GB. Some popul

 - Various open models across supported providers

+### [Vercel AI Gateway](https://vercel.com/docs/ai-gateway)
+
+Routes to various supported providers.
+
+**Limits:** [$5/month](https://vercel.com/docs/ai-gateway/pricing)
+
+
 ### [Cerebras](https://cloud.cerebras.ai/)

 Free tier restricted to 8K context.
@@ -296,7 +303,9 @@ Extremely restrictive input/output token limits.

 Distributed, decentralized crypto-based compute.
 Data is sent to individual hosts.
+**Limits:** [200 requests/day](https://chutes.ai/pricing)

+- Various open models

 ### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai)

@@ -355,7 +364,6 @@ Data is sent to individual hosts.
 Very stringent payment verification for Google Cloud.

 <table><thead><tr><th>Model Name</th><th>Model Limits</th></tr></thead><tbody>
-<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="1">10 requests/minute<br>Shared Quota</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>
@@ -440,12 +448,6 @@ Very stringent payment verification for Google Cloud.

 **Models:** Various open models

-### [CentML](https://centml.com)
-
-**Credits:** $1
-
-**Models:** Various open models
-
 ### [nCompass](https://ncompass.tech)

 **Credits:** $1
@@ -501,12 +503,19 @@ Very stringent payment verification for Google Cloud.
 **Credits:** $5 for 3 months

 **Models:**
- 
 - E5-Mistral-7B-Instruct
+- Llama 3.1 405B
 - Llama 3.1 8B
+- Llama 3.2 1B
+- Llama 3.2 3B
 - Llama 3.3 70B
 - Llama-4-Maverick-17B-128E-Instruct
+- Llama-4-Scout-17B-16E-Instruct
+- Llama-Guard-3-8B
+- Qwen/QwQ-32B
+- Qwen/Qwen2-Audio-7B-Instruct
 - Qwen/Qwen3-32B
+- Whisper-Large-v3
 - deepseek-ai/DeepSeek-R1-0528
 - deepseek-ai/DeepSeek-R1-Distill-Llama-70B
 - deepseek-ai/DeepSeek-V3-0324
@@ -517,7 +517,7 @@ def fetch_samba_models(logger):
        ret_models.append(
            {
                "id": model["model_id"],
-                "name": model["model_name"],
+                "name": model["model_name"] or model["model_id"],
            }
        )
    ret_models = sorted(ret_models, key=lambda x: x["name"])
@@ -680,8 +680,8 @@ def main():

    gemini_text_models = [
        {
-            "id": "gemini-2.5-flash-preview-04-17",
-            "name": "Gemini 2.5 Flash (Preview)",
+            "id": "gemini-2.5-flash",
+            "name": "Gemini 2.5 Flash",
            "limits": gemini_models.get("gemini-2.5-flash", {}),
        },
        {
@@ -807,6 +807,12 @@ def main():
    model_list_markdown += "- Various open models across supported providers\n"
    model_list_markdown += "\n"

+    # --- Vercel AI Gateway ---
+    model_list_markdown += "### [Vercel AI Gateway](https://vercel.com/docs/ai-gateway)\n\n"
+    model_list_markdown += "Routes to various supported providers.\n\n"
+    model_list_markdown += "**Limits:** [$5/month](https://vercel.com/docs/ai-gateway/pricing)\n\n"
+    model_list_markdown += "\n"
+
    # --- Cerebras ---
    model_list_markdown += "### [Cerebras](https://cloud.cerebras.ai/)\n\n"
    model_list_markdown += "Free tier restricted to 8K context.\n\n"
@@ -897,7 +903,9 @@ def main():
    # --- Chutes ---
    model_list_markdown += "### [Chutes](https://chutes.ai/)\n\n"
    model_list_markdown += "Distributed, decentralized crypto-based compute.\n"
-    model_list_markdown += "Data is sent to individual hosts.\n\n"
+    model_list_markdown += "Data is sent to individual hosts.\n"
+    model_list_markdown += "**Limits:** [200 requests/day](https://chutes.ai/pricing)\n\n"
+    model_list_markdown += "- Various open models\n"
    if chutes_models:
        for model in chutes_models:
            model_list_markdown += f"- {model['name']}\n"
@@ -934,13 +942,7 @@ def main():
            "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},
-        }
-    ]
+    vertex_gemini_models = []
    vertex_deepseek_models = [
        {
            "id": "deepseek-r1-0528-maas",
@@ -1067,13 +1069,6 @@ def main():
            "requirements": "",
            "models_desc": "Various open models",
        },
-        {
-            "name": "CentML",
-            "url": "https://centml.com",
-            "credits": "$1",
-            "requirements": "",
-            "models_desc": "Various open models",
-        },
        {
            "name": "nCompass",
            "url": "https://ncompass.tech",
@@ -1114,7 +1109,7 @@ def main():
        trial_list_markdown += "**Credits:** $5 for 3 months\n\n"
        trial_list_markdown += "**Models:**\n"
        for model in samba_models:
-            trial_list_markdown += f"- {model['name']}\n"
+            trial_list_markdown += f"- {model['name']}\n"   
        trial_list_markdown += "\n"

    # --- Scaleway Generative APIs (Trial - Table) ---