Listings
All listings: OpenRouter
Every listing for the models on page 16 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 |
|---|---|---|---|---|---|---|
Nous Hermes 2 Mixtral 8x7B DPO 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 93.3From 62 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.60 | $0.60 | —Not published by the provider | —Not enough data yet |
Llama 3 8B Instruct 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 93.2From 199 benchmarks. Plenty of data behind it. | ≈ 76 ±11Coding IQ 75.7, 95% interval 65–87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.03 | $0.06 | —Not published by the provider | 46.4Poor value (46.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama 3.2 11B Vision Instruct 🇺🇸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. | 92.2From 59 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.049 | $0.049 | —Not published by the provider | 56.1Good value (56.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Gemma 3n E2b It 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 90.4From 29 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.00 | $0.00 | —Not published by the provider | —Not enough data yet |
DeepSeek R1 Distill Llama 8B 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 90.0From 6 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.04 | $0.04 | —Not published by the provider | —Not enough data yet |
89.3From 51 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.10 | $0.10 | 16K | 38.1Poor value (38.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | |
Inference by Reka AI | 89.3From 51 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.10 | $0.10 | 16K | 38.1Poor value (38.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Mistral 7B Instruct v0.2 🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 88.3From 144 benchmarks. Plenty of data behind it. | ≈ 76 ±12Coding IQ 75.7, 95% interval 64–88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20 | $0.20 | —Not published by the provider | 46.7Poor value (46.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Qwen-VL Plus 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 87.7From 40 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.21 | $0.63 | —Not published by the provider | —Not enough data yet |
Mistral (7B) Instruct v0.1 🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 87.1From 34 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.11 | $0.19 | —Not published by the provider | 39.4Poor value (39.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama 3.2 3B 🇺🇸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. | 86.5From 255 benchmarks. Plenty of data behind it. | ≈ 76 ±14Coding IQ 75.7, 95% interval 62–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | —Not published by the provider | 44.3Poor value (44.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama 3.2 3B 🇺🇸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. | 86.5From 255 benchmarks. Plenty of data behind it. | ≈ 76 ±14Coding IQ 75.7, 95% interval 62–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.33 | 131K | 44.3Poor value (44.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama 3.2 3B Inference by Parasail🇺🇸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. | 86.5From 255 benchmarks. Plenty of data behind it. | ≈ 76 ±14Coding IQ 75.7, 95% interval 62–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.33 | 131K | 44.3Poor value (44.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Mistral (7B) Instruct v0.3 🇫🇷Maker headquartered in FR, 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. | 85.5From 276 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.028 | $0.054 | —Not published by the provider | 47.1Poor value (47.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
DeepSeek R1 Distill Qwen 7B 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 85.1From 72 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.10 | $0.20 | —Not published by the provider | —Not enough data yet |
Llama 3.2 1B Instruct 🇺🇸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. | 83.4From 93 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.005 | $0.01 | —Not published by the provider | 43.7Poor value (43.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
DeepSeek R1 Distill Qwen 1.5B 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 75.6From 50 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.18 | $0.18 | —Not published by the provider | —Not enough data yet |
Joey 1 🇺🇸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. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 16K | —Doesn’t apply to this model |
Joey 1 Inference by Baseten🇺🇸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. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 16K | —Doesn’t apply to this model |
Decider Flash V1.2 🇺🇸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. Newer version | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
Decider Flash V1.2 Inference by Perplexity🇺🇸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. Newer version | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
Decider Flash V1.3 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
Decider Flash V1.3 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.00 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
Decider Flash V1.3 Inference by Perplexity🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.00 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
| —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 131K | —Doesn’t apply to this model | |
Inference by Respan | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.01 | —Doesn’t apply to this model | 131K | —Doesn’t apply to this model |
| —Not enough data yet | —Not enough data yet | $0.015 | $0.015 | —Not published by the provider | —Not enough data yet | |
Deepcoder 14B Previewagentica-org/deepcoder-14b-preview:free · freeagentica-org/deepcoder-14b-preview:free · free | —Not enough data yet | —Not enough data yet | $0.00 | $0.00 | —Not published by the provider | —Not enough data yet |
Ling 3.0 Tiny 🇨🇳Maker headquartered in CN, 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 | $0.015cache read $0.003 | $0.045 | 262K | —Not enough data yet |
Granite 4.0 H Micro 🇺🇸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 | $0.017 | $0.112 | —Not published by the provider | —Not enough data yet |
clef flash 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 | $0.019 | —Doesn’t apply to this model | 25K | —Doesn’t apply to this model |
clef flash 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 | $0.038 | —Doesn’t apply to this model | 25K | —Doesn’t apply to this model |
clef flash 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 | $0.019 | —Doesn’t apply to this model | 25K | —Doesn’t apply to this model |
clef flash 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 | $0.038 | —Doesn’t apply to this model | 25K | —Doesn’t apply to this model |
| —Doesn’t apply to this model | —Doesn’t apply to this model | $0.02 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model | |
| —Doesn’t apply to this model | —Doesn’t apply to this model | $0.02 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model | |
| —Doesn’t apply to this model | —Doesn’t apply to this model | $0.02 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model | |
d1.2 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.02 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
d1.2 Inference by Liquid🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.02 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |