Skip to content

Featherless AI

Pricing page

123 listings across 100 models

4 of these models don't have a page of their own yet, so they aren't listed below. Models that only catalog hosts such as Featherless offer get a page once they have benchmark results, or once another provider sells a model from the same maker. A page stays up for 30 days after the model last qualified.

Page 2 of 4. The lists below split this page's listings into those sold by Featherless AI, run by Featherless AI, or sent to Featherless AI by a marketplace.

Sold by Featherless AI

6 listings on this page sold by Featherless AI.

Default order. 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
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it
$0.07$0.3433K
Qwen3.6 27B
$0.32$2.7033KNot measured
Qwen3.6 35B A3B
$0.186$1.113833KNot measured
GPT OSS 120B
$0.15$0.60131K
GLM 4.7 Flash
$0.0653$0.40203KNot measuredNot measured
Gemma 4 E4B-it
$0.10$0.2033KNot enough data yetNot measuredNot measured

Run by Featherless AI

25 listings on this page where Featherless AI runs the model. Another provider sells these listings.

Default order. 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
MiniMax M3
Β Hugging Face$0.55$2.20262K
MiniMax M3minimax/minimax-m3:thinking Β· thinking Β· fp8 Β· UNK
Β NanoGPT$0.5775cache read $0.063$2.31Not published by the provider
MiniMax M3fp8
Β OpenRouter$0.55cache read $0.06$2.20262K
Step 3.5 Flash
Β Hugging Faceβ€”β€”Not published by the providerNot measuredNot measured
Qwen3.5 27B
Β Hugging Faceβ€”β€”Not published by the providerNot measured
Β Hugging Faceβ€”β€”Not published by the providerNot measuredNot measured
Qwen3.6 27B
Β Hugging Faceβ€”β€”Not published by the providerNot measured
GLM 4.6
Β Hugging Faceβ€”β€”Not published by the providerNot measured
MiniMax M2.5
Β Hugging Faceβ€”β€”Not published by the providerNot measured
DeepSeek R1deepseek-ai/DeepSeek-R1-0528 Β· 0528
Β Hugging Faceβ€”β€”Not published by the provider
Kimi K2 Instruct
Β Hugging Faceβ€”β€”Not published by the providerNot measuredNot measured
Step 3.7 Flash
Β Hugging Faceβ€”β€”Not published by the providerNot measured
MiniMax M2.7
Β Hugging Faceβ€”β€”Not published by the providerNot measured
Qwen3.6 35B A3B
Β Hugging Faceβ€”β€”Not published by the providerNot measured
DeepSeek V3.1
Β Hugging Faceβ€”β€”Not published by the providerNot measured
Qwen3 CoderQwen/Qwen3-Coder-480B-A35B-Instruct
Β Hugging Faceβ€”β€”Not published by the providerNot measured
GPT OSS 120B
Β Hugging Faceβ€”β€”Not published by the provider
Qwen3 Coder Next
Β Hugging Faceβ€”β€”Not published by the providerNot measured
Β Hugging Faceβ€”β€”Not published by the providerNot measuredNot measured
Β Hugging FaceNot enough data yetβ€”β€”Not published by the providerNot measuredNot measured
GLM 4.7 Flash
Β Hugging Faceβ€”β€”Not published by the providerNot measuredNot measured
Qwen3 32B
Β Hugging Faceβ€”β€”Not published by the providerNot measured
Qwen3 30B A3B InstructQwen/Qwen3-30B-A3B-Instruct-2507
Β Hugging Faceβ€”β€”Not published by the providerNot measured
DeepSeek V3deepseek-ai/DeepSeek-V3-0324 Β· 0324
Β Hugging Faceβ€”β€”Not published by the provider
Qwen3 14B
Β Hugging Faceβ€”β€”Not published by the providerNot measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works