LLM Model Registry 48 Models • 21 Providers
Real-time token pricing, verified free rate limits, and minimum VRAM footprints.
🟢 Live Free Tier Health: 24 verified free model endpoints active today. No credit cards required.
| MODEL & FAMILY | CONTEXT | BEST API RATE ($/1M) | SPEED | FREE TIER | MIN VRAM | ACTION |
|---|---|---|---|---|---|---|
DeepSeekMoEReasoning⚡ Tools/JSON | 128K | $0.00/0.00 | 500 tok/s | — | 670GB ↗ | |
MetaDenseReasoning⚡ Tools/JSON | 128K | $0.00/0.00 | 500 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 40GB ↗ | |
Black Forest LabsDenseMultimodal | — | $0.00/0.00 | 5 tok/s | — | 12GB ↗ | |
Black Forest LabsDenseMultimodal | — | $0.00/0.00 | 6 tok/s | Together AI (Free tier)No Card | 12GB ↗ | |
Kilo GatewayProprietaryCoding⚡ Tools/JSON | 128K | $0.00/0.00 | 120 tok/s | Kilo Gateway (Daily Free Tier)No Card | Closed | |
Kilo GatewayProprietaryMultimodal⚡ Tools/JSON | 128K | $0.00/0.00 | 180 tok/s | Kilo Gateway (Free in Kilo Code)No Card | Closed | |
Zhipu AIProprietaryEdge | 128K | $0.00/0.00 | 100 tok/s | Z.ai (Permanently Free)No Card | Closed | |
GoogleProprietaryMultimodal | 1.049M Context | $0.00/0.00 | 15 tok/s | Google AI Studio ()No Card | —GB ↗ | |
Mistral AIProprietaryCoding | 128K | $0.00/0.00 | 1 tok/s | Mistral AI (La Plateforme) ()No Card | 22GB ↗ | |
DeepSeekDenseReasoning | 128K | $0.01/0.01 | 100 tok/s | — | 40GB ↗ | |
DeepSeek R1 Distill Qwen 32B ↗ DeepSeekDenseReasoning | 128K | $0.01/0.01 | 100 tok/s | OpenRouter (20 RPM)No Card | 20GB ↗ | |
MetaDenseCoding⚡ Tools/JSON | 128K | $0.01/0.01 | 800 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 6GB ↗ | |
MetaDenseEdge⚡ Tools/JSON | 128K | $0.01/0.01 | 1,500 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 2GB ↗ | |
MetaDenseEdge⚡ Tools/JSON | 128K | $0.02/0.02 | 1,200 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 3GB ↗ | |
AlibabaDenseEdge⚡ Tools/JSON | 128K | $0.04/0.04 | 300 tok/s | OpenRouter (20 RPM)No Card | 5GB ↗ | |
AlibabaDenseCoding⚡ Tools/JSON | 128K | $0.05/0.05 | 300 tok/s | OpenRouter (20 RPM)No Card | 5GB ↗ | |
Google DeepMindDenseEdge⚡ Tools/JSON | 8K | $0.05/0.05 | 550 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 6GB ↗ | |
OpenAIDenseEdge⚡ Tools/JSON | 128K | $0.05/0.05 | 400 tok/s | — | 2GB ↗ | |
Mistral AIDenseEdge⚡ Tools/JSON | 32K | $0.06/0.06 | 250 tok/s | — | 5GB ↗ | |
Mistral AIDenseEdge⚡ Tools/JSON | 128K | $0.07/0.09 | 120 tok/s | — | 8GB ↗ | |
Google DeepMindDenseGeneral⚡ Tools/JSON | 128K | $0.07/0.07 | 400 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 8GB ↗ | |
Google DeepMindProprietaryEdge⚡ Tools/JSON | 1M Context | $0.07/0.30 | 130 tok/s | Google AI Studio (15 RPM / 1M tokens/day)No Card | Closed | |
AlibabaDenseCoding⚡ Tools/JSON | 128K | $0.10/0.15 | 500 tok/s | OpenRouter (20 RPM)No Card | 20GB ↗ | |
AlibabaDenseCoding⚡ Tools/JSON | 128K | $0.10/0.10 | 120 tok/s | OpenRouter (20 RPM)No Card | 10GB ↗ | |
AlibabaDenseGeneral⚡ Tools/JSON | 128K | $0.10/0.10 | 120 tok/s | OpenRouter (20 RPM)No Card | 10GB ↗ | |
Mistral AIDenseCoding | 128K | $0.10/0.10 | 70 tok/s | — | 14GB ↗ | |
Google DeepMindDenseGeneral⚡ Tools/JSON | 8K | $0.10/0.10 | 250 tok/s | Groq (30 RPM / 14,400 RPD)No Card | 16GB ↗ | |
OpenAIDenseEdge | 16K | $0.10/0.14 | 100 tok/s | — | 10GB ↗ | |
OpenAIProprietaryReasoning⚡ Tools/JSON | 128K | $0.10/0.15 | 500 tok/s | — | Closed | |
Google DeepMindProprietaryGeneral⚡ Tools/JSON | 1M Context | $0.10/0.40 | 150 tok/s | Google AI Studio (15 RPM / 1M tokens/day)No Card | Closed | |
OpenAIProprietaryEdge⚡ Tools/JSON | 128K | $0.10/0.40 | 200 tok/s | — | Closed | |
OpenAIDenseMultimodal | — | $0.10/0.10 | 100 tok/s | — | 4GB ↗ | |
NVIDIAMoEMultimodal⚡ Tools/JSON | 128K | $0.10/0.15 | 500 tok/s | — | 70GB ↗ | |
DeepSeekMoEReasoning | 128K | $0.14/0.28 | 35 tok/s | — | 670GB ↗ | |
OpenAIProprietaryEdge⚡ Tools/JSON | 128K | $0.15/0.60 | 150 tok/s | — | Closed | |
AlibabaDenseMultimodal⚡ Tools/JSON | 128K | $0.20/0.20 | 150 tok/s | — | 5GB ↗ | |
Mistral AIProprietaryReasoning | 128K | $0.20/0.60 | 30 tok/s | — | 37GB ↗ | |
Mistral AIDenseCoding | 32K | $0.30/0.90 | 55 tok/s | — | 14GB ↗ | |
MetaDenseReasoning | 128K | $0.35/0.35 | 90 tok/s | — | 40GB ↗ | |
AlibabaDenseReasoning | 128K | $0.35/0.40 | 50 tok/s | — | 40GB ↗ | |
AlibabaDenseMultimodal | 128K | $0.35/0.40 | 45 tok/s | — | 40GB ↗ | |
Mistral AIMoEReasoning | 65K | $0.50/0.50 | 25 tok/s | — | 80GB ↗ | |
AnthropicProprietaryEdge⚡ Tools/JSON | 200K | $0.80/4.00 | 120 tok/s | — | Closed | |
OpenAIProprietaryReasoning | 128K | $1.10/4.40 | 100 tok/s | — | Closed | |
MetaDenseReasoning | 128K | $2.50/2.50 | 14 tok/s | — | 230GB ↗ | |
CohereProprietaryReasoning | 128K | $2.50/10.00 | 25 tok/s | — | Closed | |
AnthropicProprietaryReasoning | 200K | $3.00/15.00 | 80 tok/s | — | Closed | |
AnthropicProprietaryReasoning | 200K | $15.00/75.00 | 30 tok/s | — | Closed |
Data Freshness: Verified via Official Provider APIs & Documentation | Refreshed Weekly|Token pricing sourced from official provider API documentation and OpenRouter catalog.Methodology →