Listings
All listings: Requesty
Every listing for the models on page 6 of 7 of Requesty, including each model's other versions and routes. Back to Requesty
Sold by Requesty
45 listings on this page sold by Requesty.
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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|
Llama 3.3 70B Instruct 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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77 ±9Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.23 | $0.40 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Llama 3.3 70B Instruct Inference by Novita AI🇺🇸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. | 108.1From 278 benchmarks. Plenty of data behind it. | 77 ±9Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.39 | $0.39 | 131K | 31.6Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | 126.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Mistral Large Inference by Mistral AI🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | 108.0From 293 benchmarks. Plenty of data behind it. | 72 ±9Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.55 | $1.65 | 131K | 22.0Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 120Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
WizardLM 2 8x22B Inference by Novita AI🇺🇸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. | ≈ 108From 9 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.62 | $0.62 | 66K | 43.8Poor value (43.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Mistral Small 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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78 ±10Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11 | $0.33 | 33K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 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 measured |
Mistral Small 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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78 ±10Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.165 | $0.66 | 256K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 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 measured |
Mistral Small 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. | 107.8From 316 benchmarks. Plenty of data behind it. | 78 ±10Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.165 | $0.66 | 256K | 27.4Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 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 measured |
Llama 3.1 70B Instruct 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. Newer version | 106.8From 168 benchmarks. Plenty of data behind it. | ≈ 80 ±11Coding IQ 80.3, 95% interval 69–91. 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. | $0.23 | $0.40 | 131K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Qwen 2.5 Coder 32B Instruct Inference by DeepInfra🇨🇳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. | 106.3From 104 benchmarks. Plenty of data behind it. | 81 ±9Coding IQ 80.7, 95% interval 72–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.07 | $0.16 | 16K | 50.7Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Llama 3.2 90B Vision Instruct 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. | 106.1From 54 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.35 | $0.40 | 131K | 57.0Good value (57.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Phi 4 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. | 105.9From 144 benchmarks. Plenty of data behind it. | ≈ 78 ±11Coding IQ 77.6, 95% interval 66–89. 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. | $0.07 | $0.14 | 16K | 51.2Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | 129.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
open-mistral-7b Inference by Mistral AI🇫🇷Maker headquartered in FR, according to the company's own website. The citation is on the model page. | ≈ 106From 5 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.275 | $0.275 | 33K | —Not enough data yet | —Not measured | —Not measured |
GPT-4.1 nano Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75 ±9Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75 ±9Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75 ±9Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.0275 | $0.44 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75 ±9Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.11cache read $0.0275 | $0.44 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-4.1 nano Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.3From 325 benchmarks. Plenty of data behind it. | 75 ±9Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.025 | $0.40 | 1M | 27.8Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 126.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Flash Image Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 105.2From 184 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $2.50 | 1M | 60.9Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
DeepSeek R1 Distill Llama 70B Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 97.6From 6 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.23 | $0.69 | 64K | —Not enough data yet | —Not measured | —Not measured |
Llama 3.1 8B Instruct Inference by Novita AI🇺🇸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 | 95.6From 343 benchmarks. Plenty of data behind it. | 70 ±9Coding IQ 69.9, 95% interval 61–79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05 | $0.05 | 16K | 39.5Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Inference by Novita AI | 94.2From 6 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.05 | $0.05 | 8K | —Not enough data yet | —Not measured | —Not measured |
Qwen3.5 2B Inference by DeepInfra🇨🇳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. | 92.6From 66 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.02 | $0.10 | 262K | —Not enough data yet | —Not measured | —Not measured |
Llama 3.1 8B Instruct Turbo 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 | $0.02 | $0.05 | 131K | 24.9Poor value (24.9). Costs more per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Baichuan M2 32B Inference by Novita AIOpen 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 | $0.07 | $0.07 | 131K | —Not enough data yet | —Not measured | —Not measured |
MythoMax L2 13b Inference by Novita AIOpen 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 | $0.09 | $0.09 | 4K | —Not enough data yet | —Not measured | —Not measured |
Qwen3 Coder 480B A35B Instruct Turbo Inference by DeepInfra🇨🇳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 | $0.30cache read $0.10 | $1.00 | 262K | —Not enough data yet | —Not measured | —Not measured |
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 | $0.30cache read $0.08 | $1.50cache write $0.30 | 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. | —Not measured | —Not measured |
Doubao Seed 2.0 Codedeepinfra/ByteDance/Seed-2.0-codedeepinfra/ByteDance/Seed-2.0-code Inference by DeepInfra | —Not enough data yet | —Not enough data yet | $0.50cache read $0.10 | $3.00 | 256K | —Not enough data yet | —Not measured | —Not measured |
DeepSeek R1 (Turbo) Inference by Novita AI🇨🇳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 | $0.70 | $2.50 | 64K | —Not enough data yet | —Not measured | —Not measured |
Perplexity Sonar Inference by Perplexity🇺🇸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 | $1.00 | $1.00 | 131K | —Not enough data yet | —Not measured | —Not measured |
Inkling 256K Inference by Thinking Machines🇺🇸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 | $1.87cache read $0.374 | $4.68 | 262K | —Not enough data yet | —Not measured | —Not measured |
Grok 4.20 (Reasoning) Inference by xAI🇺🇸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 | $2.00>200k $4.00cache read $0.20 | $6.00>200k $12.00cache write $2.00 | 2M | —Not enough data yet | —Not measured | —Not measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)