Listings
All listings: NanoGPT
Every listing for the models on page 20 of 40 of NanoGPT, including each model's other versions and routes. Back to NanoGPT
Sold by NanoGPT
37 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 |
|---|---|---|---|---|---|---|
nanogpt/coding-router:high 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 |
ERNIE Light DT 1.0 (Intl) 🇨🇳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 | $1.30cache read $0.13 | $4.50 | 1M | —Not enough data yet |
DeepSeek R1 Distill Qwen 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 | $1.40cache read $0.70 | $1.40 | 16K | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $1.50cache read $0.275 | $4.50 | 1M | —Not enough data yet | |
CyberHeabsynvfp4 · 🇨🇦 CAnvfp4 · 🇨🇦 CA Inference by Heabsy | —Not enough data yet | —Not enough data yet | $1.50cache read $0.27 | $4.50 | —Not published by the provider | —Not enough data yet |
Cogito V1 Preview Qwen 32B 🇺🇸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 | $1.80cache read $0.90 | $1.80 | 128K | —Not enough data yet |
Cogito V1 Preview Qwen 32B Inference by Kitani🇺🇸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 | $1.869cache read $0.9345 | $1.869 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $2.00cache read $1.00 | $6.00 | 8K | —Not enough data yet | |
Fugu Max 🇯🇵Maker headquartered in JP, according to the company's own website. The citation is on the model page. | —Not enough data yet | —Not enough data yet | $2.00cache read $0.25 | $6.00 | 1M | —Not enough data yet |
Gemini Pro 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 | $2.00cache read $0.20 | $12.00 | 1M | 57.4Good value (57.4). Cheaper 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 | $2.00cache read $0.35 | $5.00 | 1M | —Not enough data yet | |
OrcaCyber K3.1 ProSG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $2.10cache read $0.3675 | $5.25 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $2.00 | $10.00 | 128K | —Not enough data yet | |
Eva Llama 3.33 70b v0.0 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 | $2.006cache read $1.003 | $2.006 | 33K | —Not enough data yet |
EVA-LLaMA-3.33-70B-v0.1 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 | $2.006cache read $1.003 | $2.006 | 33K | —Not enough data yet |
Command A Reasoning 08 2025 🇺🇸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 | $2.50cache read $1.25 | $10.00 | 256K | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $2.50cache read $0.25 | $7.50 | 262K | —Not enough data yet | |
Magnum v4 72B 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 | $2.65cache read $1.325 | $5.30 | 16K | —Not enough data yet |
Command R Plus 08 2024 🇺🇸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 | $2.856cache read $1.428 | $14.246 | 128K | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $3.00cache read $0.30 | $5.00 | 1M | —Not enough data yet | |
Abliterated Model Largefp8 · 🇺🇸 USfp8 · 🇺🇸 US Inference by Abliteration | —Not enough data yet | —Not enough data yet | $3.15cache read $0.315 | $5.25 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $3.00cache read $0.30 | $5.00 | 1M | —Not enough data yet | |
Abliterated Model Large V2fp8 · 🇺🇸 USfp8 · 🇺🇸 US Inference by Abliteration | —Not enough data yet | —Not enough data yet | $3.15cache read $0.315 | $5.25 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $3.00cache read $0.75 | $6.00 | 131K | 40.7Poor value (40.7). 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 | $3.15cache read $0.7875 | $6.30 | —Not published by the provider | 40.7Poor value (40.7). 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 | $3.00cache read $0.30 | $15.00 | 1M | —Not enough data yet | |
Ember 1🇺🇸 US🇺🇸 US Inference by Fireworks AI | —Not enough data yet | —Not enough data yet | $3.15cache read $0.315 | $15.75 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $3.00cache read $0.30 | $5.00 | 999K | —Not enough data yet | |
OrcaCyber GLM 5.3SG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $3.15cache read $0.315 | $5.25 | —Not published by the provider | —Not enough data yet |
OrcaCyber Zero 1.0 Newer version | —Not enough data yet | —Not enough data yet | $3.00cache read $0.75 | $7.50 | 999K | —Not enough data yet |
OrcaCyber Zero 1.0 Inference by OrcarouterNewer version | —Not enough data yet | —Not enough data yet | $3.15cache read $0.7875 | $7.875 | —Not published by the provider | —Not enough data yet |
| —Not enough data yet | —Not enough data yet | $3.00cache read $0.75 | $7.50 | 999K | —Not enough data yet | |
OrcaCyber Zero 1.5SG/US/JPSG/US/JP Inference by Orcarouter | —Not enough data yet | —Not enough data yet | $3.15cache read $0.7875 | $7.875 | —Not published by the provider | —Not enough data yet |
Kimi K3.1 Pro Abliterated (Lyber)lyber/kimi-k3.1-pro-abliteratedlyber/kimi-k3.1-pro-abliterated | —Not enough data yet | —Not enough data yet | $4.00 | $15.00 | 1M | —Not enough data yet |
Kimi K3.1 Pro Abliterated (Lyber)lyber/kimi-k3.1-pro-abliterated · UNKlyber/kimi-k3.1-pro-abliterated · UNK Inference by Lyber | —Not enough data yet | —Not enough data yet | $4.20 | $15.75 | —Not published by the provider | —Not enough data yet |
Qwen 3.8 Max Prime 🇨🇳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 | $4.00cache read $0.50 | $12.00 | 1M | —Not enough data yet |
Qwen 3.8 Max Prime 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 | $4.20cache read $0.525 | $12.60 | —Not published by the provider | —Not enough data yet |