Skip to content

Listings

All listings: DeepInfra

Every listing for the models on page 8 of 11 of DeepInfra, including each model's other versions and routes. Back to DeepInfra

Sold by DeepInfra

25 listings on this page sold by DeepInfra.

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
Not enough data yetNot enough data yet$0.04$0.058KNot enough data yet
Nemotron 3.5 Rerank 8B BF16
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
bf16
Not enough data yetNot enough data yet$0.05—33KNot enough data yet
Qwen3 Reranker 8B
🇨🇳
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 yetNot enough data yet$0.05—33KNot enough data yet
Llama Guard 3 8B
🇺🇸
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$0.055$0.055131K
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Gemma 4 31B It Turbo
🇺🇸
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$0.09cache read $0.05$0.34262KNot enough data yet
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
🇺🇸
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.
deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
Not enough data yetNot enough data yet$0.10$0.40131KNot enough data yet
Llama Guard 4 12B
🇺🇸
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$0.18$0.18164K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
GPT Oss 120b Ultra
🇺🇸
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$0.20$0.95131KNot enough data yet
Nemotron 3.5 Content Safety
🇺🇸
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.
nvidia/Nemotron-Content-Safety-3.5 · bf16
Not enough data yetNot enough data yet$0.20$0.20131KNot enough data yet
Gemma 4 31B It Ultra
🇺🇸
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$0.27$0.76131KNot enough data yet
olmocr-7b sold by DeepInfra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
deepinfra/allenai/olmOCR-7B-0725-FP8 · fp8+0725 · fp8
Not enough data yetNot enough data yet$0.27$1.5016KNot enough data yet
Qwen3 Coder 480B A35B Instruct Turbo
🇨🇳
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 yetNot enough data yet$0.30cache read $0.10$1.00262KNot enough data yet
MiniMax M2.7 Turbo
🇨🇳
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 yetNot enough data yet$0.38cache read $0.07$1.70197KNot enough data yet
Meta Llama 3.1 70B Instruct Turbo
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama 3.3 70B Instruct TurboWe compared the version names in our catalogue.
Not enough data yetNot enough data yet$0.40$0.40131K
33.0
Poor value (33.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
MythoMax L2 13b
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$0.40$0.404KNot enough data yet
Doubao Seed 2.0 CodeByteDance/Seed-2.0-code
Not enough data yetNot enough data yet$0.50cache read $0.10$3.00256KNot enough data yet
NVIDIA: Llama 3.1 Nemotron 70B Instruct
🇺🇸
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.
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct
Not enough data yetNot enough data yet$0.60$0.60131KNot enough data yet
L3.3 70b Euryale v2.3
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$0.65$0.75131KNot enough data yet
Not enough data yetNot enough data yet$0.85$0.85131KNot enough data yet
DeepSeek-R1-0528-Turbo
🇨🇳
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$1.00$3.0033KNot enough data yet
DeepSeek R1 (Turbo)
🇨🇳
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 yetNot enough data yet$1.00$3.0041KNot enough data yet
Nousresearch Hermes 3 Llama 3.1 405b
🇺🇸
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.
deepinfra/NousResearch/Hermes-3-Llama-3.1-405B
Not enough data yetNot enough data yet$1.00$1.00131KNot enough data yet
BGE M3 Multi
🇨🇳
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——Not published by the providerNot enough data yet
BGE M3 Multi 8k
🇨🇳
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——Not published by the providerNot enough data yet
Bria 3.2
🇮🇱
Maker headquartered in IL, 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

Run by DeepInfra

15 listings on this page where DeepInfra runs the model. Another provider sells these listings.

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
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
Qwen3 Reranker 8B
🇨🇳
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.
 LlmgatewayNot enough data yetNot enough data yet$0.05—Not published by the providerNot enough data yet
Llama Guard 3 8B
🇺🇸
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.
 Eden AINot enough data yetNot enough data yet$0.055$0.055131K
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama Guard 4 12B
🇺🇸
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.
 Eden AINot enough data yetNot enough data yet$0.18$0.18164K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama Guard 4 12B
🇺🇸
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.
 Hugging FaceNot enough data yetNot enough data yet$0.18$0.18164K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama Guard 4 12B
🇺🇸
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.
bf16
 OpenRouterNot enough data yetNot enough data yet$0.18$0.18164K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama Guard 4 12B
🇺🇸
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.
bf16/flex · bf16
 OpenRouterNot enough data yetNot enough data yet$0.144$0.144164K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Llama Guard 4 12B
🇺🇸
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.
bf16/priority · bf16
 OpenRouterNot enough data yetNot enough data yet$0.27$0.27164K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Nemotron 3.5 Content Safety
🇺🇸
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.
bf16 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$0.21$0.21Not published by the providerNot enough data yet
Nemotron 3.5 Content Safety
🇺🇸
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.
bf16
 OpenRouterNot enough data yetNot enough data yet$0.20$0.20131KNot enough data yet
Qwen3 Coder 480B A35B Instruct Turbo
🇨🇳
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.
 RequestyNot enough data yetNot enough data yet$0.30cache read $0.10$1.00262KNot enough data yet
MythoMax L2 13b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
 Eden AINot enough data yetNot enough data yet$0.40$0.404KNot enough data yet
Doubao Seed 2.0 Codedeepinfra/ByteDance/Seed-2.0-code
 Eden AINot enough data yetNot enough data yet$0.50cache read $0.10$3.00256KNot enough data yet
Doubao Seed 2.0 Codedeepinfra/ByteDance/Seed-2.0-code
 RequestyNot enough data yetNot enough data yet$0.50cache read $0.10$3.00256KNot enough data yet
NVIDIA: Llama 3.1 Nemotron 70B Instruct
🇺🇸
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.
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct
 Eden AINot enough data yetNot enough data yet$0.60$0.60131KNot enough data yet
Nousresearch Hermes 3 Llama 3.1 405b
🇺🇸
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.
deepinfra/NousResearch/Hermes-3-Llama-3.1-405B
 Eden AINot enough data yetNot enough data yet$1.00$1.00131KNot enough data yet

How this data works