Listings
All listings: NanoGPT
Every listing for the models on page 19 of 40 of NanoGPT, including each model's other versions and routes. Back to NanoGPT
Sold by NanoGPT
45 listings on this page sold by NanoGPT.
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 |
|---|---|---|---|---|---|---|
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 | $0.6999cache read $0.35 | $0.6999 | 33K | —Not enough data yet |
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 |
Aion 3.0 Mini Inference by AionlabsNewer version | —Not enough data yet | —Not enough data yet | $0.735cache read $0.189 | $1.47 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.70cache read $0.18 | $1.40 | 262K | —Not enough data yet | |
Inference by Aionlabs | —Not enough data yet | —Not enough data yet | $0.735cache read $0.189 | $1.47 | —Not published by the provider | —Not enough data yet |
DeepSeek R1 Llama 70B Abliterated 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 | $0.70cache read $0.35 | $0.70 | 16K | —Not enough data yet |
Llama 3.3 70B Instruct abliterated 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 | $0.70cache read $0.35 | $0.70 | 33K | —Not enough data yet |
Qwen 2.5 32B Abliterated 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 | $0.70cache read $0.35 | $0.70 | 33K | —Not enough data yet |
Qwen 2.5 32B Abliterated Inference by KitaniOpen 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 | $0.714cache read $0.357 | $0.714 | —Not published by the provider | —Not enough data yet |
Wayfarer Large 70b Llama 3.3 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 | $0.70cache read $0.35 | $0.70 | 33K | —Not enough data yet |
Gemini Flash Latest 🇺🇸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 | $0.75cache read $0.075 | $3.75 | 1M | 46.3Poor value (46.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Doubao Seed 2.0 Code Previewdoubao-seed-2-0-code-preview-260215 · 260215doubao-seed-2-0-code-preview-260215 · 260215 | —Not enough data yet | —Not enough data yet | $0.782cache read $0.391 | $3.893 | 256K | —Not enough data yet |
LongCat 2.5 Preview 🇨🇳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 | $0.7875cache read $0.0158 | $3.0975 | 1M | —Not enough data yet |
EVA-Qwen2.5-32B-v0.2 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 | $0.799cache read $0.3995 | $0.799 | 16K | —Not enough data yet |
EVA-Qwen2.5-32B-v0.2 Inference by KitaniOpen 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 | $0.818cache read $0.409 | $0.818 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.80cache read $0.20 | $1.60 | 131K | 44.4Poor value (44.4). 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 | $0.84cache read $0.21 | $1.68 | —Not published by the provider | 44.4Poor value (44.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | |
Llama 3.1 8b (uncensored) 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 | $0.80cache read $0.40 | $1.60 | 33K | —Not enough data yet |
Llama 3.1 8b (uncensored) Inference by AionlabsOpen 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 | $0.84 | $1.68 | —Not published by the provider | —Not enough data yet |
Llama 3.1 8b (uncensored) Inference by KitaniOpen 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 | $0.819cache read $0.4095 | $1.659 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 1M | —Not enough data yet | |
Orcacyber Flash 1.0orca/orcacyber-flash-1.0:thinking · thinkingorca/orcacyber-flash-1.0:thinking · thinking | —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 1M | —Not enough data yet |
Orcacyber Flash 1.0SG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
Orcacyber Flash 1.0orca/orcacyber-flash-1.0:thinking · thinking · SG/US/JPorca/orcacyber-flash-1.0:thinking · thinking · SG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 1M | —Not enough data yet | |
OrcaCyber GLM 5.3 FlashSG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
OrcaCyber Hy4 NewReleased 4 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 1M | —Not enough data yet |
OrcaCyber Hy4 Inference by OrcarouterNewReleased 4 Nov 2026 | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
OrcaCyber MiMo V2.6 Flashorca/orcacyber-mimo-flashorca/orcacyber-mimo-flash | —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 1M | —Not enough data yet |
OrcaCyber MiMo V2.6 Flashorca/orcacyber-mimo-flash · SG/US/JPorca/orcacyber-mimo-flash · SG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 262K | —Not enough data yet | |
OrcaCyber MiniMax M3.1 FlashSG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.80cache read $0.15 | $1.60 | 262K | —Not enough data yet | |
OrcaCyber Qwen3.8 Flash NextSG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $0.84cache read $0.1575 | $1.68 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $0.80cache read $0.03 | $3.20 | 1M | —Not enough data yet | |
Qwen 3.8 27B Uncensored Fast by Heabsyheabsy/qwen3.8-27b-uncensored-fastheabsy/qwen3.8-27b-uncensored-fast | —Not enough data yet | —Not enough data yet | $1.00cache read $0.22 | $3.00 | 1M | —Not enough data yet |
Qwen 3.8 27B Uncensored Fast by Heabsyheabsy/qwen3.8-27b-uncensored-fast · nvfp4 · EEAheabsy/qwen3.8-27b-uncensored-fast · nvfp4 · EEA Inference by Heabsy | —Not enough data yet | —Not enough data yet | $0.8299cache read $0.1501 | $2.62 | —Not published by the provider | —Not enough data yet |
Abliterated Model 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 | $1.00cache read $0.10 | $3.00 | 262K | —Not enough data yet |
Abliterated Model Inference by AbliterationOpen 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 | $1.05cache read $0.105 | $3.15 | —Not published by the provider | —Not enough data yet |
Abliterated Large Flashabliteration-ai/abliterated-model-large-flashabliteration-ai/abliterated-model-large-flash | —Not enough data yet | —Not enough data yet | $1.00cache read $0.10 | $2.00 | 1M | —Not enough data yet |
Abliterated Large Flashabliteration-ai/abliterated-model-large-flash · fp8 · 🇺🇸 USabliteration-ai/abliterated-model-large-flash · fp8 · 🇺🇸 US Inference by Abliteration | —Not enough data yet | —Not enough data yet | $1.05cache read $0.105 | $2.10 | —Not published by the provider | —Not enough data yet |
GLM 5.3 Uncensored 🇨🇳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 | $1.25cache read $0.30 | $2.25 | 1M | —Not enough data yet |
GLM 5.3 Uncensored Inference by Arnict🇨🇳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 | $1.0385cache read $0.2518 | $2.0874 | —Not published by the provider | —Not enough data yet |
GLM 5.3 Uncensored Inference by Entrim🇨🇳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 | $1.0395cache read $0.252 | $2.0895 | —Not published by the provider | —Not enough data yet |
nanogpt/coding-router RouterThis is a router, not a fixed model. The provider chooses which model answers, and that choice can change. | —Not enough data yet | —Not enough data yet | $1.10cache read $0.11 | $2.20 | 1M | —Not enough data yet |