Skip to content

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
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
nanogpt/coding-router:high
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
nanogpt/coding-router:high · coding+high
Not enough data yetNot enough data yet$1.10cache read $0.11$2.201MNot 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 yetNot enough data yet$1.30cache read $0.13$4.501MNot 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 yetNot enough data yet$1.40cache read $0.70$1.4016KNot enough data yet
Not enough data yetNot enough data yet$1.50cache read $0.275$4.501MNot enough data yet
CyberHeabsynvfp4 · 🇨🇦 CA
Inference by Heabsy
Not enough data yetNot enough data yet$1.50cache read $0.27$4.50Not published by the providerNot 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 yetNot enough data yet$1.80cache read $0.90$1.80128KNot 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.
int4 · GLB
Inference by Kitani
Not enough data yetNot enough data yet$1.869cache read $0.9345$1.869Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$2.00cache read $1.00$6.008KNot 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 yetNot enough data yet$2.00cache read $0.25$6.001MNot 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 yetNot enough data yet$2.00cache read $0.20$12.001M
57.4
Good 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 yetNot enough data yet$2.00cache read $0.35$5.001MNot enough data yet
OrcaCyber K3.1 ProSG/US/JP
Inference by Orcarouter
Not enough data yetNot enough data yet$2.10cache read $0.3675$5.25Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$2.00$10.00128KNot 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 yetNot enough data yet$2.006cache read $1.003$2.00633KNot 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 yetNot enough data yet$2.006cache read $1.003$2.00633KNot 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 yetNot enough data yet$2.50cache read $1.25$10.00256KNot enough data yet
Not enough data yetNot enough data yet$2.50cache read $0.25$7.50262KNot 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 yetNot enough data yet$2.65cache read $1.325$5.3016KNot 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 yetNot enough data yet$2.856cache read $1.428$14.246128KNot enough data yet
Not enough data yetNot enough data yet$3.00cache read $0.30$5.001MNot enough data yet
Abliterated Model Largefp8 · 🇺🇸 US
Inference by Abliteration
Not enough data yetNot enough data yet$3.15cache read $0.315$5.25Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$3.00cache read $0.30$5.001MNot enough data yet
Abliterated Model Large V2fp8 · 🇺🇸 US
Inference by Abliteration
Not enough data yetNot enough data yet$3.15cache read $0.315$5.25Not published by the providerNot enough data yet
Aion 3.0
Newer version
Newer versionAion 3.5We compared release dates and version names in our catalogue.
Not enough data yetNot enough data yet$3.00cache read $0.75$6.00131K
40.7
Poor value (40.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Aion 3.0
Newer version
Newer versionAion 3.5We compared release dates and version names in our catalogue.
Inference by Aionlabs
Not enough data yetNot enough data yet$3.15cache read $0.7875$6.30Not published by the provider
40.7
Poor 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 yetNot enough data yet$3.00cache read $0.30$15.001MNot enough data yet
Ember 1🇺🇸 US
Inference by Fireworks AI
Not enough data yetNot enough data yet$3.15cache read $0.315$15.75Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$3.00cache read $0.30$5.00999KNot enough data yet
OrcaCyber GLM 5.3SG/US/JP
Inference by Orcarouter
Not enough data yetNot enough data yet$3.15cache read $0.315$5.25Not published by the providerNot enough data yet
OrcaCyber Zero 1.0
Newer version
Newer versionOrcaCyber Zero 1.5We compared the version names in our catalogue.
Not enough data yetNot enough data yet$3.00cache read $0.75$7.50999KNot enough data yet
OrcaCyber Zero 1.0
Newer version
Newer versionOrcaCyber Zero 1.5We compared the version names in our catalogue.
SG/US/JP
Inference by Orcarouter
Not enough data yetNot enough data yet$3.15cache read $0.7875$7.875Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$3.00cache read $0.75$7.50999KNot enough data yet
OrcaCyber Zero 1.5SG/US/JP
Inference by Orcarouter
Not enough data yetNot enough data yet$3.15cache read $0.7875$7.875Not published by the providerNot enough data yet
Kimi K3.1 Pro Abliterated (Lyber)lyber/kimi-k3.1-pro-abliterated
Not enough data yetNot enough data yet$4.00$15.001MNot enough data yet
Kimi K3.1 Pro Abliterated (Lyber)lyber/kimi-k3.1-pro-abliterated · UNK
Inference by Lyber
Not enough data yetNot enough data yet$4.20$15.75Not published by the providerNot 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 yetNot enough data yet$4.00cache read $0.50$12.001MNot 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.
🇸🇬 SG
Inference by Alibaba Cloud
Not enough data yetNot enough data yet$4.20cache read $0.525$12.60Not published by the providerNot enough data yet

How this data works