Listings
All listings: OpenRouter
Every listing for the models on page 20 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
39 listings on this page sold by OpenRouter.
Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value |
|---|---|---|---|---|---|---|
Clef Omni Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.15 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Clef Omni Inference by Cloudflare Workers AIOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.15 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Command R 08 2024 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.15 | $0.60 | 128K | —Not enough data yet |
Command R 08 2024 Inference by Cohere🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.15 | $0.60 | 128K | —Not enough data yet |
DaisyRose 27B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. NewReleased 18 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.15cache read $0.0375 | $1.875 | 262K | —Not enough data yet |
DaisyRose 27B Inference by DeepInfraOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. NewReleased 18 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.15cache read $0.0375 | $1.875 | 262K | —Not enough data yet |
GPT-4o-mini Search Preview 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.15 | $0.60 | —Not published by the provider | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
LFM-40b 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.15 | $0.15 | —Not published by the provider | —Not enough data yet |
Perceptron Mk1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | —Not enough data yet | —Not enough data yet | $0.15 | $1.50 | 33K | 51.0Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Perceptron Mk1 Inference by Perceptron🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | —Not enough data yet | —Not enough data yet | $0.15 | $1.50 | 33K | 51.0Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Perceptron Mk1.5 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.15 | $1.50 | 37K | —Not enough data yet |
Perceptron Mk1.5 Inference by Perceptron🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.15 | $1.50 | 37K | —Not enough data yet |
RNJ-1 Instruct Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.15 | $0.15 | —Not published by the provider | —Not enough data yet |
Cogito V2 Preview Llama 109B 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.18 | $0.59 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.18 | $0.18 | —Not published by the provider | —Not enough data yet | |
Nous-Hermes-Llama2-13b 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.18 | $0.18 | —Not published by the provider | —Not enough data yet |
Spotlight 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.18 | $0.18 | —Not published by the provider | 39.9Poor value (39.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Clef 27B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.192 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Clef 27B Inference by Cloudflare Workers AIOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.24 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Clef 27B Inference by DeepInfraOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.192 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Clef 27B Inference by PrimeintellectOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.24 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Qwen3 Coder Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.195cache read $0.039 | $0.975cache write $0.2438 | 1M | 42.8Poor value (42.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Qwen3 Coder Flash Inference by Alibaba Cloud🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.195cache read $0.039 | $0.975cache write $0.2438 | 998K | 42.8Poor value (42.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
dobby-mini-unhinged-plus-llama-3.1-8b 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20 | $0.20 | —Not published by the provider | —Not enough data yet |
Dolphin Mistral 24B Venice Edition Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.00 | $0.00 | —Not published by the provider | —Not enough data yet |
Dolphin Mistral 24B Venice Edition Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.20 | $0.90 | 128K | —Not enough data yet |
Dolphin Mistral 24B Venice Edition Inference by VeniceOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.20 | $0.90 | 128K | —Not enough data yet |
llama-3.1-lumimaid-8b 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20 | $1.25 | —Not published by the provider | —Not enough data yet |
llama-3.1-sonar-small-128k-online 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20 | $0.20 | —Not published by the provider | —Not enough data yet |
llama-3-lumimaid-8b 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | —Not enough data yet | —Not enough data yet | $0.20 | $1.25 | —Not published by the provider | —Not enough data yet |
LlamaGuard 2 8B 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | —Not enough data yet | —Not enough data yet | $0.20 | $0.20 | —Not published by the provider | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
midm-k-3.0-pro 🇰🇷Maker headquartered in KR, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20cache read $0.04 | $0.80 | 262K | —Not enough data yet |
midm-k-3.0-pro Inference by Kt🇰🇷Maker headquartered in KR, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20cache read $0.04 | $0.80 | 262K | —Not enough data yet |
Mistral Saba 🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20cache read $0.02 | $0.60 | 33K | —Not enough data yet |
Mistral Saba Inference by Mistral AI🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.20cache read $0.02 | $0.60 | 33K | —Not enough data yet |
Nemotron 3.5 Content Safety 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.20 | $0.20 | 131K | —Not enough data yet |
Nemotron 3.5 Content Safety Inference by DeepInfra🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | —Not enough data yet | —Not enough data yet | $0.20 | $0.20 | 131K | —Not enough data yet |
Olmo 2 32B Instruct 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | —Not enough data yet | —Not enough data yet | $0.20 | $0.35 | —Not published by the provider | —Not enough data yet |
GLM Z1 32B 0414 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.24 | $0.24 | —Not published by the provider | —Not enough data yet |