Skip to content

Together AI

Pricing page

506 listings across 336 models

Page 4 of 14. The lists below split this page's listings into those sold by Together AI, run by Together AI, or sent to Together AI by a marketplace.

Sold by Together AI

27 listings on this page sold by Together 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
Qwen2.5 72B
Not enough data yet——131KNot enough data yetNot measured
——131KNot enough data yetNot measuredNot measured
Qwen3.5 9B
$0.17$0.25262KNot measured
Qwen3.5 9BQwen/Qwen3.5-9B-FP8 · fp8
——262KNot measured
Devstral Small 25052505
——131KNot measuredNot measured
Qwen3 8B
——41KNot measured
$3.50$3.504KNot measuredNot measured
Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · fp8
$0.27$0.85Not published by the provider
Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP4 · fp4
——1M
GPT OSS 20b
$0.05$0.20131K
Ministral 3 14B Instructmistralai/Ministral-3-14B-Instruct-2512 · 2512
Not enough data yet$0.20$0.20262KNot enough data yetNot measuredNot measured
Nemotron Nano 9b V2nvidia/NVIDIA-Nemotron-Nano-9B-v2
Not enough data yet$0.06$0.25131KNot measuredNot measured
Veo 3.1
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Not enough data yet——131KNot enough data yetNot measured
Nemotron 3 Nano 30B A3Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 · bf16
——262KNot measuredNot measured
Qwen2.5 14B
Not enough data yet——131KNot enough data yetNot measuredNot measured
Magistral Small 2509mistralai/Magistral-Small-2506 · 2506
Not enough data yet——41KNot measuredNot measured
Not enough data yet$1.04$1.04131KNot measuredNot measured
——33KNot enough data yetNot measuredNot measured
$1.20$1.2033KNot measuredNot measured
Not enough data yet$1.95$8.0033KNot measuredNot measured
Not enough data yet——262KNot enough data yetNot measuredNot measured
——66KNot measured
——131KNot measured
Qwen2.5 32B
Not enough data yet——131KNot enough data yetNot measuredNot measured
Not enough data yet$1.20$1.20Not published by the providerNot measuredNot measured
Qwen2 72B Instruct
$0.90$0.9033KNot measuredNot measured

Run by Together AI

7 listings on this page where Together 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
Qwen3.5 9B
 Hugging Face$0.17$0.25262KNot measured
Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · fp8
 Hugging Face$0.27$0.851M
GPT OSS 20b
 Hugging Face$0.05$0.20131K
 Hugging Face$0.88$0.88131KNot measured
Show all 7 listings

Showing 4 of 7: one listing for each model.

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

How this data works