Skip to content

Listings

All listings: OpenRouter

Every listing for the models on page 22 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter

Sold by OpenRouter

40 listings on this page sold by OpenRouter.

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
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYap
UnslopNemo 12B
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$0.401MNot enough data yetNot measured
UnslopNemo 12B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
bf16
Inference by Parasail
Not enough data yetNot enough data yet$0.40$0.401MNot enough data yetNot measured
Morph V3 Large
🇺🇸
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$0.90$1.90262K
38.4
Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Morph V3 Large
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
morph/morph-v3-large:batch · batch
Not enough data yetNot enough data yet$0.45$0.95262K
38.4
Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Morph V3 Large
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
morph/morph-v3-large:batch · batch+fp8 · fp8
Inference by Morph
Not enough data yetNot enough data yet$0.45$0.95262K
38.4
Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Morph V3 Large
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
fp8
Inference by Morph
Not enough data yetNot enough data yet$0.90$1.90262K
38.4
Poor value (38.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Not enough data yetNot enough data yet$0.50$0.50Not published by the providerNot enough data yetNot measured
Coder Large
🇺🇸
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$0.50$0.80Not published by the providerNot enough data yetNot measured
DeepSeek Prover V2
🇨🇳
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$0.50$2.18Not published by the providerNot enough data yetNot measured
Not enough data yetNot enough data yet$0.50$0.50Not published by the providerNot enough data yetNot measured
Jamba Instruct
🇮🇱
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$0.50$0.70Not published by the providerNot enough data yetNot measured
Not enough data yetNot enough data yet$0.50$0.80Not published by the providerNot enough data yetNot measured
virtuoso-medium-v2
🇺🇸
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$0.50$0.80Not published by the providerNot enough data yetNot measured
Not enough data yetNot enough data yet$0.55$0.85Not published by the providerNot enough data yetNot measured
Skyfall 36B V2
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$0.55cache read $0.25$0.8033K
41.9
Poor value (41.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Skyfall 36B V2
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Parasail
Not enough data yetNot enough data yet$0.55cache read $0.25$0.8033K
41.9
Poor value (41.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Ring 1t
🇨🇳
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$0.57$2.28Not published by the provider
55.3
Good value (55.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Step3
🇨🇳
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$0.57$1.42Not published by the providerNot enough data yetNot measured
Elorian Glimpseelorian/glimpse
Not enough data yetNot enough data yet$0.60cache read $0.06$3.00262KNot enough data yetNot measured
Elorian Glimpseelorian/glimpse
Inference by Together AI
Not enough data yetNot enough data yet$0.60cache read $0.06$3.00262KNot enough data yetNot measured
GPT Audio Mini
🇺🇸
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$0.60$2.40128KNot enough data yetNot measured
GPT Audio Mini
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by OpenAI
Not enough data yetNot enough data yet$0.60$2.40128KNot enough data yetNot measured
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1
🇺🇸
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/llama-3.1-nemotron-ultra-253b-v1
Not enough data yetNot enough data yet$0.60$1.80Not published by the providerNot enough data yetNot measured
Palmyra X5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionPalmyra X6We compared the version names in our catalogue.
Not enough data yetNot enough data yet$0.60$6.001M
45.3
Poor value (45.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Palmyra X5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionPalmyra X6We compared the version names in our catalogue.
Inference by Amazon Web Services
Not enough data yetNot enough data yet$0.60$6.001M
45.3
Poor value (45.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Pro Preview 06-05
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Pro PreviewWe compared the version names in our catalogue.
google/gemini-2.5-pro-preview
Not enough data yetNot enough data yet$1.25cache read $0.125$10.001M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
59 ±9
Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Gemini 2.5 Pro Preview 06-05
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Pro PreviewWe compared the version names in our catalogue.
google/gemini-2.5-pro-preview
Inference by Google
Not enough data yetNot enough data yet$1.25cache read $0.125$10.001M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
59 ±9
Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Gemini 2.5 Pro Preview 06-05
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Pro PreviewWe compared the version names in our catalogue.
google/gemini-2.5-pro-preview · flex
Inference by Google
Not enough data yetNot enough data yet$0.625cache read $0.0625$5.001M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
59 ±9
Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Gemini 2.5 Pro Preview 06-05
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Pro PreviewWe compared the version names in our catalogue.
google/gemini-2.5-pro-preview · priority
Inference by Google
Not enough data yetNot enough data yet$2.25cache read $0.225$18.001M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
59 ±9
Chatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not enough data yetNot enough data yet$0.65$1.00Not published by the providerNot enough data yetNot measured
L3.1 Euryale 70b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionL3.3 Euryale 70bWe compared the version names in our catalogue.
Not enough data yetNot enough data yet$0.85$0.85131KNot enough data yetNot measured
L3.1 Euryale 70b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionL3.3 Euryale 70bWe compared the version names in our catalogue.
fp8
Inference by DeepInfra
Not enough data yetNot enough data yet$0.85$0.85131KNot enough data yetNot measured
L3.1 Euryale 70b
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionL3.3 Euryale 70bWe compared the version names in our catalogue.
fp8/flex · fp8
Inference by DeepInfra
Not enough data yetNot enough data yet$0.68$0.68131KNot enough data yetNot measured
Aion-1.0-Mini
Newer version
Newer versionAion 3.5 MiniWe compared the version names in our catalogue.
Not enough data yetNot enough data yet$0.70$1.40Not published by the provider
49.4
Fair value (49.4). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Aion 3.0 Mini
Newer version
Newer versionAion 3.5 MiniWe compared release dates and version names in our catalogue.
Not enough data yetNot enough data yet$0.70cache read $0.18$1.40131KNot enough data yetNot measured
Aion 3.0 Mini
Newer version
Newer versionAion 3.5 MiniWe compared release dates and version names in our catalogue.
Inference by Aionlabs
Not enough data yetNot enough data yet$0.70cache read $0.18$1.40131KNot enough data yetNot measured
Not enough data yetNot enough data yet$0.70cache read $0.18$1.40262KNot enough data yetNot measured
Inference by Aionlabs
Not enough data yetNot enough data yet$0.70cache read $0.18$1.40262KNot enough data yetNot measured
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 yetNot enough data yet$0.70$0.95Not published by the providerNot enough data yetNot measured
Not enough data yetNot enough data yet$0.70$0.80Not published by the providerNot enough data yetNot measured

How this data works