Listings
All listings: OpenRouter
Every listing for the models on page 21 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
44 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 |
|---|---|---|---|---|---|---|
GLM-z1-rumination-32b π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.24 | $0.24 | βNot published by the provider | βNot enough data yet |
Mixtral 8x7B Instruct π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.24 | $0.24 | βNot published by the provider | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
| βNot enough data yet | βNot enough data yet | $0.25 | $1.00 | βNot published by the provider | 50.3Fair value (50.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | |
Mercury Coder Smallmercury-coder-small-beta Β· betamercury-coder-small-beta Β· beta | βNot enough data yet | βNot enough data yet | $0.25 | $1.00 | βNot published by the provider | βNot enough data yet |
Mistral Tiny π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.25 | $0.25 | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.25 | $0.50 | βNot published by the provider | βNot enough data yet | |
Qwen3.5 Plus π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.26 | $1.56 | 1M | βNot enough data yet |
Qwen3.5 Plus Inference by Alibaba Cloudπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.26 | $1.56 | 984K | βNot enough data yet |
Kimi Dev 72B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.29 | $1.15 | βNot published by the provider | 53.6Good value (53.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Kimi Dev 72B π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.00 | $0.00 | βNot published by the provider | 53.6Good value (53.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Command A Plus πΊπΈMaker 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. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.15 | $1.50 | 192K | βNot enough data yet |
Command A Plus Inference by CohereπΊπΈMaker 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. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.15 | $1.50 | 128K | βNot enough data yet |
Cydonia 24B V4.1 Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | βNot enough data yet | βNot enough data yet | $0.30cache read $0.15 | $0.50 | 131K | 55.4Good value (55.4). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Cydonia 24B V4.1 Inference by ParasailOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | βNot enough data yet | βNot enough data yet | $0.30cache read $0.15 | $0.50 | 131K | 55.4Good value (55.4). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
| βNot enough data yet | βNot enough data yet | $0.30 | $1.20 | βNot published by the provider | βNot enough data yet | |
DeepSeek R1t Chimeratngtech/deepseek-r1t-chimera:free Β· freetngtech/deepseek-r1t-chimera:free Β· free | βNot enough data yet | βNot enough data yet | $0.00 | $0.00 | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.30 | $1.20 | βNot published by the provider | βNot enough data yet | |
DeepSeek R1T2 Chimeratngtech/deepseek-r1t2-chimera:free Β· freetngtech/deepseek-r1t2-chimera:free Β· free | βNot enough data yet | βNot enough data yet | $0.00 | $0.00 | βNot published by the provider | βNot enough data yet |
KAT-Coder-Pro V2 π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.06 | $1.20 | βNot published by the provider | 59.5Good value (59.5). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
MiniMax-M2 Her π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.03 | $1.20 | βNot published by the provider | 40.5Poor value (40.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
mai-ds-r1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.30 | $1.20 | βNot published by the provider | 40.0Poor value (40.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
mai-ds-r1 πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.00 | $0.00 | βNot published by the provider | 40.0Poor value (40.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
| βNot enough data yet | βNot enough data yet | $0.30 | $2.50 | 32K | βNot enough data yet | |
Moondream 3.1 9B A2Bfp8fp8 Inference by Primeintellect | βNot enough data yet | βNot enough data yet | $0.30 | $2.50 | 32K | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | $0.30 | $2.50 | 32K | βNot enough data yet | |
Moondream 3 Previewfp8fp8 Inference by Primeintellect | βNot enough data yet | βNot enough data yet | $0.30 | $2.50 | 32K | βNot enough data yet |
Motif 3 Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.06 | $1.20 | 262K | βNot enough data yet |
Motif 3 Inference by KtOpen weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.06 | $1.20 | 262K | βNot enough data yet |
ReMM SLERP L2 13B Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.20 | $0.50 | 6K | βNot enough data yet |
ReMM SLERP 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. | βNot enough data yet | βNot enough data yet | $0.30cache read $0.20 | $0.50 | 6K | βNot enough data yet |
Weaver (alpha) πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.30 | $0.50 | 8K | βNot enough data yet |
Weaver (alpha) Inference by Mancer 2πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.30 | $0.50 | 8K | βNot enough data yet |
Mistral Small 3.1 24B Instruct π«π·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. Newer version | βNot enough data yet | βNot enough data yet | $0.00 | $0.00 | βNot published by the provider | βNot enough data yet |
Mistral Small 3.1 24B Instruct π«π·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. Newer version | βNot enough data yet | βNot enough data yet | $0.351 | $0.555 | 128K | βNot enough data yet |
Mistral Small 3.1 24B Instruct Inference by Cloudflare Workers AIπ«π·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. Newer version | βNot enough data yet | βNot enough data yet | $0.351 | $0.555 | 128K | βNot enough data yet |
GLM 5.3 FlashX π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.37cache read $0.075 | $1.25 | 1M | 57.1Good value (57.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
GLM 5.3 FlashX Inference by Z.aiπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.37cache read $0.075 | $1.25 | 1M | 57.1Good value (57.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
GLM 5.3 FlashX Legal π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.37cache read $0.075 | $1.25 | 1M | βNot enough data yet |
GLM 5.3 FlashX Legal Inference by Z.aiπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.37cache read $0.075 | $1.25 | 1M | βNot enough data yet |
Morph V3 Fast πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.80 | $1.20 | 262K | 37.9Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Morph V3 Fast πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.40 | $0.60 | 82K | 37.9Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Morph V3 Fast Inference by MorphπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.40 | $0.60 | 82K | 37.9Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Morph V3 Fast Inference by MorphπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.80 | $1.20 | 262K | 37.9Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 πΊπΈMaker 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. | βNot enough data yet | βNot enough data yet | $0.40 | $0.40 | βNot published by the provider | βNot enough data yet |