Listings
All listings: OpenRouter
Every listing for the models on page 19 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
49 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 |
|---|---|---|---|---|---|---|
Tencent: Hy-MT2-7B 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 | $0.074 | $0.295 | 8K | —Not enough data yet |
Tencent: Hy-MT2-7B Inference by TencentOpen 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 | $0.074 | $0.295 | 8K | —Not enough data yet |
Nex N2.5 Pro 🇨🇳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 | $0.075cache read $0.015 | $0.25 | 262K | —Not enough data yet |
Nex N2.5 Pro Inference by Nex Agi🇨🇳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 | $0.075cache read $0.015 | $0.25 | 262K | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.075 | $0.30 | —Not published by the provider | 46.0Poor value (46.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | |
| —Not enough data yet | —Not enough data yet | $0.075cache read $0.0375 | $0.50 | 262K | —Not enough data yet | |
Ternary Bonsai 2 27Bint4int4 Inference by Darkbloom | —Not enough data yet | —Not enough data yet | $0.075cache read $0.0375 | $0.50 | 262K | —Not enough data yet |
LFM3 1.7B 🇺🇸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 | $0.08cache read $0.02 | $0.20 | 262K | —Not enough data yet |
LFM3 1.7B 🇺🇸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 | $0.00 | $0.00 | 262K | —Not enough data yet |
LFM3 1.7B Inference by Liquid🇺🇸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 | $0.08cache read $0.02 | $0.20 | 262K | —Not enough data yet |
LFM3 1.7B Inference by Liquid🇺🇸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 | $0.00 | $0.00 | 262K | —Not enough data yet |
MythoMax L2 13b 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 | $0.30cache read $0.20 | $0.50 | 8K | —Not enough data yet |
MythoMax L2 13b Inference by Mancer 2Open 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 | $0.30cache read $0.20 | $0.50 | 8K | —Not enough data yet |
MythoMax L2 13b 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 | $0.08 | $0.11 | 4K | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.08cache read $0.04 | $0.13 | 262K | —Not enough data yet | |
Ternary Bonsai 2 9Bint4int4 Inference by Darkbloom | —Not enough data yet | —Not enough data yet | $0.08cache read $0.04 | $0.13 | 262K | —Not enough data yet |
Tongyi DeepResearch 30B A3B 🇨🇳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 | $0.09 | $0.40 | —Not published by the provider | 52.0Fair value (52.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Tongyi DeepResearch 30B A3B 🇨🇳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 | $0.00 | $0.00 | —Not published by the provider | 52.0Fair value (52.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Neversleep Llama 3.1 Lumimaid 8bneversleep/llama-3.1-lumimaid-8bneversleep/llama-3.1-lumimaid-8b | —Not enough data yet | —Not enough data yet | $0.0938 | $0.75 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.0938 | $0.75 | —Not published by the provider | —Not enough data yet | |
Bison 1 Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. NewReleased 20 Nov 2026 | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.10 | —Doesn’t apply to this model | 33K | —Doesn’t apply to this model |
Bison 1 Inference by BasetenOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. NewReleased 20 Nov 2026 | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.10 | —Doesn’t apply to this model | 33K | —Doesn’t apply to this model |
Cloudflare: Clairic 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 | $0.10 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Cloudflare: Clairic 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 | $0.10 | —Doesn’t apply to this model | 66K | —Doesn’t apply to this model |
Gemini Decision 1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.10 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
Gemini Decision 1 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | —Doesn’t apply to this model | —Doesn’t apply to this model | $0.10 | —Doesn’t apply to this model | 262K | —Doesn’t apply to this model |
GPT-6 Luna Decisions 🇺🇸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 | $0.10 | —Doesn’t apply to this model | 1.1M | —Doesn’t apply to this model |
GPT-6 Luna Decisions Inference by OpenAI🇺🇸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 | $0.10 | —Doesn’t apply to this model | 1.1M | —Doesn’t apply to this model |
Mammoth 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 | $0.10 | —Doesn’t apply to this model | 16K | —Doesn’t apply to this model |
Mammoth 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 | $0.10 | —Doesn’t apply to this model | 16K | —Doesn’t apply to this model |
Muse Spark 1.3 Contributor 🇺🇸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 | $0.10cache read $0.002 | $0.20 | 1M | 67.1Good value (67.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Muse Spark 1.3 Contributor Inference by Meta🇺🇸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 | $0.10cache read $0.002 | $0.20 | 1M | 67.1Good value (67.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Phi-3.5 Mini 128K Instruct 🇺🇸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 | $0.10 | $0.10 | —Not published by the provider | 44.9Poor value (44.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Ripple 65B Preview NewReleased 4 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.10cache read $0.025 | $0.30 | 1M | —Not enough data yet |
Ripple 65B Preview Inference by PrimeintellectNewReleased 4 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.10cache read $0.025 | $0.30 | 1M | —Not enough data yet |
Ripple 65B Preview Inference by Together AINewReleased 4 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.20cache read $0.02 | $0.60 | 131K | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.10 | $0.20 | 128K | —Not enough data yet | |
UI TARS 1.5 7Bbf16bf16 Inference by Parasail | —Not enough data yet | —Not enough data yet | $0.10 | $0.20 | 128K | —Not enough data yet |
Voxtral Small 24B 🇫🇷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. | —Not enough data yet | —Not enough data yet | $0.10cache read $0.01 | $0.30 | 33K | 51.5Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Voxtral Small 24B Inference by Mistral AI🇫🇷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. | —Not enough data yet | —Not enough data yet | $0.11cache read $0.011 | $0.33 | 32K | 51.5Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Nex N2.6 🇨🇳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 | $0.12cache read $0.024 | $0.40 | 262K | —Not enough data yet |
Nex N2.6 Inference by Nex Agi🇨🇳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 | $0.12cache read $0.024 | $0.40 | 262K | —Not enough data yet |
NVIDIA: Llama 3.1 Nemotron 70B 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. | —Not enough data yet | —Not enough data yet | $0.12 | $0.30 | —Not published by the provider | —Not enough data yet |
Hermes 4 70B 🇺🇸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 | $0.13 | $0.40 | —Not published by the provider | 54.0Good value (54.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
ERNIE 4.5 VL 28B A3B 🇨🇳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 | $0.14 | $0.56 | —Not published by the provider | 39.7Poor value (39.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama Guard 4 12B 🇺🇸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 | $0.18 | $0.18 | 164K | 50.2Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama Guard 4 12B 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 | $0.18 | $0.18 | 164K | 50.2Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama Guard 4 12B 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 | $0.144 | $0.144 | 164K | 50.2Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Llama Guard 4 12B 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 | $0.27 | $0.27 | 164K | 50.2Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. |