Skip to content

Listings

All listings: Llmgateway Providers

Every listing for the models on page 10 of 10 of Llmgateway Providers, including each model's other versions and routes. Back to Llmgateway Providers

Sold by Llmgateway Providers

24 listings on this page sold by Llmgateway Providers.

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
GLM-5.3 (CanopyWave)
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
canopywave/glm-5.3
Not enough data yetNot enough data yet$1.40cache read $0.26$4.401MNot enough data yet
Kimi K3.1 Pro (CanopyWave)
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
canopywave/kimi-k3.1-pro
Not enough data yetNot enough data yet$1.90cache read $0.19$9.501MNot enough data yet
Claude Sonnet 5 (Azure Anthropic)azure-anthropic/claude-sonnet-5
Not enough data yetNot enough data yet$2.00cache read $0.20$10.00cache write $2.501MNot enough data yet
Claude Sonnet 5.5 (Azure Anthropic)azure-anthropic/claude-sonnet-5-5
Not enough data yetNot enough data yet$2.00cache read $0.10$10.00cache write $2.501MNot 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.
inference.net/kimi-k3.1-pro
🇺🇸
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$2.00cache read $0.20$10.001MNot enough data yet
Gemini 3.1 Pro (Preview) (Quartz)quartz/gemini-3.1-pro-preview
Not enough data yetNot enough data yet$2.00cache read $0.20$12.001MNot enough data yet
GLM-4.5 X
🇨🇳
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$2.20cache read $0.45$8.90128KNot enough data yet
GPT-4o Transcribe
🇺🇸
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$2.50$10.0016K
58.3
Good value (58.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Kimi K3 (CanopyWave)
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
canopywave/kimi-k3
Not enough data yetNot enough data yet$2.70cache read $0.27$13.501MNot enough data yet
GLM 5.3 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$2.80cache read $0.56$8.801MNot enough data yet
Kimi K3 (Baidu)
🇨🇳
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.
baidu/kimi-k3
Not enough data yetNot enough data yet$3.00cache read $0.30$15.001MNot enough data yet
Claude Opus 5.5 (Azure Anthropic)azure-anthropic/claude-opus-5-5
Not enough data yetNot enough data yet$4.00cache read $0.20$20.00cache write $5.001MNot enough data yet
Kimi K3.1 Pro 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 $0.20$20.001MNot enough data yet
Claude Opus 4.6 (Azure Anthropic)azure-anthropic/claude-opus-4-6
Not enough data yetNot enough data yet$5.00cache read $0.50$25.00cache write $6.251MNot enough data yet
Claude Opus 4.7 (Azure Anthropic)azure-anthropic/claude-opus-4-7
Not enough data yetNot enough data yet$5.00cache read $0.50$25.00cache write $6.251MNot enough data yet
Claude Opus 4.8 (Azure Anthropic)azure-anthropic/claude-opus-4-8
Not enough data yetNot enough data yet$5.00cache read $0.50$25.00cache write $6.251MNot enough data yet
Claude Opus 5 (Azure Anthropic)azure-anthropic/claude-opus-5
Not enough data yetNot enough data yet$5.00cache read $0.50$25.00cache write $6.251MNot enough data yet
Fugu Ultra v2
🇯🇵
Maker headquartered in JP, according to the company's own website. The citation is on the model page.
sakana/fugu-ultra-v2.0
Not enough data yetNot enough data yet$5.00cache read $0.50$30.001MNot enough data yet
Claude Fable 5 (Azure Anthropic)azure-anthropic/claude-fable-5
Not enough data yetNot enough data yet$10.00cache read $1.00$50.00cache write $12.501MNot enough data yet
Claude Fable 5.1 (Azure Anthropic)azure-anthropic/claude-fable-5-1
Not enough data yetNot enough data yet$10.00cache read $0.25$50.00cache write $12.501MNot enough data yet
GPT Live Transcribe
🇺🇸
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——Not published by the provider
48.6
Fair value (48.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
GPT Transcribe
🇺🇸
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——Not published by the providerNot enough data yet

How this data works