Listings
All listings: OpenRouter
Every listing for the models on page 22 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
40 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
- Yap
- Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap |
|---|---|---|---|---|---|---|---|
UnslopNemo 12B 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 | $0.40 | $0.40 | 1M | —Not enough data yet | —Not measured |
UnslopNemo 12B Inference by ParasailOpen 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 | $0.40 | $0.40 | 1M | —Not enough data yet | —Not measured |
Morph V3 Large 🇺🇸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 | $0.90 | $1.90 | 262K | 38.4Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Morph V3 Large 🇺🇸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 | $0.45 | $0.95 | 262K | 38.4Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Morph V3 Large Inference by Morph🇺🇸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 | $0.45 | $0.95 | 262K | 38.4Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Morph V3 Large Inference by Morph🇺🇸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 | $0.90 | $1.90 | 262K | 38.4Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
| —Not enough data yet | —Not enough data yet | $0.50 | $0.50 | —Not published by the provider | —Not enough data yet | —Not measured | |
Coder Large 🇺🇸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 | $0.50 | $0.80 | —Not published by the provider | —Not enough data yet | —Not measured |
DeepSeek Prover V2 🇨🇳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 | $0.50 | $2.18 | —Not published by the provider | —Not enough data yet | —Not measured |
| —Not enough data yet | —Not enough data yet | $0.50 | $0.50 | —Not published by the provider | —Not enough data yet | —Not measured | |
Jamba Instruct 🇮🇱Maker headquartered in IL, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $0.50 | $0.70 | —Not published by the provider | —Not enough data yet | —Not measured |
| —Not enough data yet | —Not enough data yet | $0.50 | $0.80 | —Not published by the provider | —Not enough data yet | —Not measured | |
virtuoso-medium-v2 🇺🇸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 | $0.50 | $0.80 | —Not published by the provider | —Not enough data yet | —Not measured |
| —Not enough data yet | —Not enough data yet | $0.55 | $0.85 | —Not published by the provider | —Not enough data yet | —Not measured | |
Skyfall 36B V2 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 | $0.55cache read $0.25 | $0.80 | 33K | 41.9Poor value (41.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Skyfall 36B V2 Inference by ParasailOpen 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 | $0.55cache read $0.25 | $0.80 | 33K | 41.9Poor value (41.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Ring 1t 🇨🇳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 | $0.57 | $2.28 | —Not published by the provider | 55.3Good value (55.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Step3 🇨🇳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 | $0.57 | $1.42 | —Not published by the provider | —Not enough data yet | —Not measured |
Elorian Glimpseelorian/glimpseelorian/glimpse | —Not enough data yet | —Not enough data yet | $0.60cache read $0.06 | $3.00 | 262K | —Not enough data yet | —Not measured |
Elorian Glimpseelorian/glimpseelorian/glimpse Inference by Together AI | —Not enough data yet | —Not enough data yet | $0.60cache read $0.06 | $3.00 | 262K | —Not enough data yet | —Not measured |
GPT Audio Mini 🇺🇸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 | $0.60 | $2.40 | 128K | —Not enough data yet | —Not measured |
GPT Audio Mini Inference by OpenAI🇺🇸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 | $0.60 | $2.40 | 128K | —Not enough data yet | —Not measured |
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 🇺🇸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 | $0.60 | $1.80 | —Not published by the provider | —Not enough data yet | —Not measured |
Palmyra X5 🇺🇸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 | $0.60 | $6.00 | 1M | 45.3Poor value (45.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Palmyra X5 Inference by Amazon Web Services🇺🇸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 | $0.60 | $6.00 | 1M | 45.3Poor value (45.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Gemini 2.5 Pro Preview 06-05 🇺🇸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 | $1.25cache read $0.125 | $10.00 | 1M | 38.2Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 59 ±9Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. |
Gemini 2.5 Pro Preview 06-05 Inference by Google🇺🇸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 | $1.25cache read $0.125 | $10.00 | 1M | 38.2Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 59 ±9Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. |
Gemini 2.5 Pro Preview 06-05 Inference by Google🇺🇸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 | $0.625cache read $0.0625 | $5.00 | 1M | 38.2Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 59 ±9Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. |
Gemini 2.5 Pro Preview 06-05 Inference by Google🇺🇸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 | $2.25cache read $0.225 | $18.00 | 1M | 38.2Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 59 ±9Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. |
| —Not enough data yet | —Not enough data yet | $0.65 | $1.00 | —Not published by the provider | —Not enough data yet | —Not measured | |
L3.1 Euryale 70b Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | —Not enough data yet | —Not enough data yet | $0.85 | $0.85 | 131K | —Not enough data yet | —Not measured |
L3.1 Euryale 70b Inference by DeepInfraOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | —Not enough data yet | —Not enough data yet | $0.85 | $0.85 | 131K | —Not enough data yet | —Not measured |
L3.1 Euryale 70b Inference by DeepInfraOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | —Not enough data yet | —Not enough data yet | $0.68 | $0.68 | 131K | —Not enough data yet | —Not measured |
Aion-1.0-Mini Newer version | —Not enough data yet | —Not enough data yet | $0.70 | $1.40 | —Not published by the provider | 49.4Fair value (49.4). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured |
Aion 3.0 Mini Newer version | —Not enough data yet | —Not enough data yet | $0.70cache read $0.18 | $1.40 | 131K | —Not enough data yet | —Not measured |
Aion 3.0 Mini Inference by AionlabsNewer version | —Not enough data yet | —Not enough data yet | $0.70cache read $0.18 | $1.40 | 131K | —Not enough data yet | —Not measured |
| —Not enough data yet | —Not enough data yet | $0.70cache read $0.18 | $1.40 | 262K | —Not enough data yet | —Not measured | |
Inference by Aionlabs | —Not enough data yet | —Not enough data yet | $0.70cache read $0.18 | $1.40 | 262K | —Not enough data yet | —Not measured |
L3.3 Electra R1 70b 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 | $0.70 | $0.95 | —Not published by the provider | —Not enough data yet | —Not measured |
| —Not enough data yet | —Not enough data yet | $0.70 | $0.80 | —Not published by the provider | —Not enough data yet | —Not measured |