Skip to content

Listings

All listings: OpenRouter

Every listing for the models on page 21 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter

Sold by OpenRouter

44 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
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValue
GLM-z1-rumination-32b
πŸ‡¨πŸ‡³
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$0.24$0.24Not published by the providerNot enough data yet
Mixtral 8x7B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.24$0.24Not published by the provider
40.6
Poor value (40.6). 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$0.25$1.00Not published by the provider
50.3
Fair value (50.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Mercury Coder Smallmercury-coder-small-beta Β· beta
Not enough data yetNot enough data yet$0.25$1.00Not published by the providerNot enough data yet
Mistral Tiny
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.25$0.25Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$0.25$0.50Not published by the providerNot enough data yet
Qwen3.5 Plus
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen/qwen3.5-plus-02-15
Not enough data yetNot enough data yet$0.26$1.561MNot enough data yet
Qwen3.5 Plus
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
qwen/qwen3.5-plus-02-15
Inference by Alibaba Cloud
Not enough data yetNot enough data yet$0.26$1.56984KNot enough data yet
Kimi Dev 72B
πŸ‡¨πŸ‡³
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$0.29$1.15Not published by the provider
53.6
Good value (53.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Kimi Dev 72B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
moonshotai/kimi-dev-72b:free Β· free
Not enough data yetNot enough data yet$0.00$0.00Not published by the provider
53.6
Good value (53.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Command A Plus
πŸ‡ΊπŸ‡Έ
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$0.30cache read $0.15$1.50192KNot enough data yet
Command A Plus
πŸ‡ΊπŸ‡Έ
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.
fp8
Inference by Cohere
Not enough data yetNot enough data yet$0.30cache read $0.15$1.50128KNot enough data yet
Cydonia 24B V4.1
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionCydonia-24B-v4.3We compared release dates and version names in our catalogue.
Not enough data yetNot enough data yet$0.30cache read $0.15$0.50131K
55.4
Good value (55.4). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Cydonia 24B V4.1
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionCydonia-24B-v4.3We compared release dates and version names in our catalogue.
bf16
Inference by Parasail
Not enough data yetNot enough data yet$0.30cache read $0.15$0.50131K
55.4
Good value (55.4). 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$0.30$1.20Not published by the providerNot enough data yet
DeepSeek R1t Chimeratngtech/deepseek-r1t-chimera:free Β· free
Not enough data yetNot enough data yet$0.00$0.00Not published by the providerNot enough data yet
Not enough data yetNot enough data yet$0.30$1.20Not published by the providerNot enough data yet
DeepSeek R1T2 Chimeratngtech/deepseek-r1t2-chimera:free Β· free
Not enough data yetNot enough data yet$0.00$0.00Not published by the providerNot enough data yet
KAT-Coder-Pro V2
πŸ‡¨πŸ‡³
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$0.30cache read $0.06$1.20Not published by the provider
59.5
Good value (59.5). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
MiniMax-M2 Her
πŸ‡¨πŸ‡³
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$0.30cache read $0.03$1.20Not published by the provider
40.5
Poor value (40.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
mai-ds-r1
πŸ‡ΊπŸ‡Έ
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$0.30$1.20Not published by the provider
40.0
Poor value (40.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
mai-ds-r1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
microsoft/mai-ds-r1:free Β· free
Not enough data yetNot enough data yet$0.00$0.00Not published by the provider
40.0
Poor value (40.0). 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$0.30$2.5032KNot enough data yet
Inference by Primeintellect
Not enough data yetNot enough data yet$0.30$2.5032KNot enough data yet
Not enough data yetNot enough data yet$0.30$2.5032KNot enough data yet
Inference by Primeintellect
Not enough data yetNot enough data yet$0.30$2.5032KNot enough data yet
Motif 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$0.30cache read $0.06$1.20262KNot enough data yet
Motif 3
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Kt
Not enough data yetNot enough data yet$0.30cache read $0.06$1.20262KNot enough data yet
ReMM SLERP 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$0.30cache read $0.20$0.506KNot enough data yet
ReMM SLERP L2 13B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Mancer 2
Not enough data yetNot enough data yet$0.30cache read $0.20$0.506KNot enough data yet
Weaver (alpha)
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
mancer/weaver
Not enough data yetNot enough data yet$0.30$0.508KNot enough data yet
Weaver (alpha)
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
mancer/weaver Β· fp8
Inference by Mancer 2
Not enough data yetNot enough data yet$0.30$0.508KNot enough data yet
Mistral Small 3.1 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, 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.
Newer version
Newer versionMistral Small 3.2 24B InstructWe compared the version names in our catalogue.
mistralai/mistral-small-3.1-24b-instruct:free Β· free
Not enough data yetNot enough data yet$0.00$0.00Not published by the providerNot enough data yet
Mistral Small 3.1 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, 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.
Newer version
Newer versionMistral Small 3.2 24B InstructWe compared the version names in our catalogue.
Not enough data yetNot enough data yet$0.351$0.555128KNot enough data yet
Mistral Small 3.1 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, 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.
Newer version
Newer versionMistral Small 3.2 24B InstructWe compared the version names in our catalogue.
Inference by Cloudflare Workers AI
Not enough data yetNot enough data yet$0.351$0.555128KNot enough data yet
GLM 5.3 FlashX
πŸ‡¨πŸ‡³
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$0.37cache read $0.075$1.251M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
GLM 5.3 FlashX
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp8
Inference by Z.ai
Not enough data yetNot enough data yet$0.37cache read $0.075$1.251M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
GLM 5.3 FlashX Legal
πŸ‡¨πŸ‡³
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$0.37cache read $0.075$1.251MNot enough data yet
GLM 5.3 FlashX Legal
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp8
Inference by Z.ai
Not enough data yetNot enough data yet$0.37cache read $0.075$1.251MNot enough data yet
Morph V3 Fast
πŸ‡ΊπŸ‡Έ
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$0.80$1.20262K
37.9
Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Morph V3 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
morph/morph-v3-fast:batch Β· batch
Not enough data yetNot enough data yet$0.40$0.6082K
37.9
Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Morph V3 Fast
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
morph/morph-v3-fast:batch Β· batch+us
Inference by Morph
Not enough data yetNot enough data yet$0.40$0.6082K
37.9
Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Morph V3 Fast
πŸ‡ΊπŸ‡Έ
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$0.80$1.20262K
37.9
Poor value (37.9). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
πŸ‡ΊπŸ‡Έ
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-3.3-nemotron-super-49b-v1.5
Not enough data yetNot enough data yet$0.40$0.40Not published by the providerNot enough data yet

How this data works