diff --git a/README.md b/README.md
index bf5f77b..1c3b02f 100644
--- a/README.md
+++ b/README.md
@@ -141,7 +141,12 @@ This lists various services that provide free access or credits towards API-base
| Free for a limited time |
Nous Hermes 3 Llama 3.1 405B (FP8) |
|
-
+
+ | Mistral (Codestral) |
+ Currently free to use, monthly subscription based, requires phone number verification. |
+ Codestral |
+ 30 requests/minute
2000 requests/day |
+
## Providers with trial credits
diff --git a/src/pull_available_models.py b/src/pull_available_models.py
index 058a1e1..f6379e6 100644
--- a/src/pull_available_models.py
+++ b/src/pull_available_models.py
@@ -397,21 +397,12 @@ def main():
groq_models = fetch_groq_models()
for idx, model in enumerate(groq_models):
- # markdown_table += f"|{'[Groq](https://console.groq.com)' if idx == 0 else '^'}|{ ' ' if idx == 0 else '^'}|{model['name']}|{get_human_limits(model)}|\n"
table += f"{f'| Groq | ' if idx == 0 else ''}{ f' | ' if idx == 0 else ''}{model['name']} | {get_human_limits(model)} |
\n"
openrouter_models = fetch_openrouter_models()
for idx, model in enumerate(openrouter_models):
- # markdown_table += f"|{'[OpenRouter](https://openrouter.ai)' if idx == 0 else '^'}|{ ' ' if idx == 0 else '^'}|{model['name']}|{get_human_limits(model)}|\n"
table += f"{f'| OpenRouter | ' if idx == 0 else ''}{ f' | ' if idx == 0 else ''}{model['name']} | {get_human_limits(model)} |
\n"
- # markdown_table += "|[Google AI Studio](https://aistudio.google.com)|Free tier Gemini API access not available within UK/CH/EEA/EU.
Data is used for training.|Gemini 1.5 Flash|15 requests/min
1500 requests/day
1 million tokens/min|\n"
- # markdown_table += "|^|^|Gemini 1.5 Pro|2 requests/min
50 requests/day
32000 tokens/min|\n"
- # markdown_table += "|^|^|Gemini 1.0 Pro|15 requests/min
15000 requests/day
32000 tokens/min|\n"
- # markdown_table += "|^|Embeddings are available in UK/CH/EEA/EU.|text-embedding-004|1500 requests/min
100 contents/batch|\n"
- # markdown_table += (
- # "|^|^|embedding-001|1500 requests/min
100 contents/batch|\n"
- # )
gemini_models = fetch_gemini_limits()
table += f"""
| Google AI Studio |
@@ -448,8 +439,6 @@ def main():
|
"""
- # markdown_table += "|[Cohere](https://cohere.com)|10 requests/min
1000 requests/month|Command-R||\n"
- # markdown_table += "|^|^|Command-R+||\n"
table += """
| Cohere |
10 requests/min
1000 requests/month |
@@ -461,7 +450,6 @@ def main():
Shared Limit |
"""
- # markdown_table += "|[HuggingFace Serverless Inference](https://huggingface.co/docs/api-inference/en/index)|Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB.|Various open models||\n"
table += """
| HuggingFace Serverless Inference |
Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. |
@@ -471,17 +459,14 @@ def main():
hyperbolic_models = fetch_hyperbolic_models()
for idx, model in enumerate(hyperbolic_models):
- # markdown_table += f"|{'[Hyperbolic](https://app.hyperbolic.xyz/)' if idx == 0 else '^'}|{ ' ' if idx == 0 else '^'}|{model['name']}| |\n"
table += f"
{f'| Hyperbolic (Free Testing Period) | ' if idx == 0 else ''}{ f' | ' if idx == 0 else ''}{model['name']} | {get_human_limits(model)} |
\n"
ovh_models = fetch_ovh_models()
for idx, model in enumerate(ovh_models):
- # markdown_table += f"|{'[OVH AI Endpoints (Free Alpha)](https://endpoints.ai.cloud.ovh.net/)' if idx == 0 else '^'}|{ 'Token expires every 2 weeks.' if idx == 0 else '^'}|{model['name']}|{get_human_limits(model)}|\n"
table += f"{f'| OVH AI Endpoints (Free Alpha) | ' if idx == 0 else ''}{ f'Token expires every 2 weeks. | ' if idx == 0 else ''}{model['name']} | {get_human_limits(model)} |
\n"
cloudflare_models = fetch_cloudflare_models()
for idx, model in enumerate(cloudflare_models):
- # markdown_table += f"|{'[Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai)' if idx == 0 else '^'}|{ '10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.' if idx == 0 else '^'}|{model['name']}| |\n"
table += f"{f'| Cloudflare Workers AI | ' if idx == 0 else ''}{ f'10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models. | ' if idx == 0 else ''}{model['name']} | |
\n"
table += """
@@ -490,6 +475,13 @@ def main():
| Nous Hermes 3 Llama 3.1 405B (FP8) |
|
"""
+
+ table += """
+ | Mistral (Codestral) |
+ Currently free to use, monthly subscription based, requires phone number verification. |
+ Codestral |
+ 30 requests/minute
2000 requests/day |
+
"""
table += ""