LLM Reference
Together AI

Together AI Models — Pricing & Benchmarks

106 models available

Together AI hosts 106 AI models in this catalog. The lowest listed input price is Gemma 3n 4B (free) at $0.02/1M input tokens. LLM Reference lets you compare these models across all 80 providers without switching tabs.

ModelInput (per 1M)Output (per 1M)Context
Gemma 3n 4B (free)$0.02$0.048k
Together AI - Gemma 3n-e4B$0.02$0.048k
Together AI TinyLlama-1.1B-Chat-v1.0$0.05$0.052k
Gemma 2B Instruct$0.1$0.12k
Mistral Small 3$0.1$0.333k
Mistral Small 3.1 24B Instruct$0.1$0.3128k
Phi-2$0.1$0.12k
Qwen1.5-0.5B$0.1$0.132k
Qwen1.5-1.8B$0.1$0.132k
Qwen1.5-4B$0.1$0.132k
Qwen3.5-9B$0.1$0.15262k
Together AI - Llama 3 8B Lite$0.1$0.18k
Together AI Llama-2-7B-chat$0.1$0.14k
gpt-oss-120b$0.15$0.6131k
Qwen2.5-7B-Instruct$0.15$0.15128k
Together AI Gemma-7B-it$0.15$0.158k
Together AI Llama-2-13B-chat$0.15$0.154k
Together AI Qwen2-7B-Instruct$0.15$0.1533k
Llama 3 8B Instruct$0.18$0.188k
Llama 3.1 8B Instruct$0.18$0.18128k
Alpaca 7B$0.2$0.22k
CodeLlama 7B$0.2$0.2100k
CodeLlama 7B Python$0.2$0.2100k
Gemma 7B Instruct$0.2$0.28k
GPT-JT Moderation 6B$0.2$0.2
Llama 2 7B 32K$0.2$0.232k
Llama 2 7B Chat$0.2$0.24k
Llama Guard 7B$0.2$0.22k
Mistral 7B Instruct v0.2$0.2$0.232k
Mistral 7B OpenOrca$0.2$0.28k
Mistral 7B v0.1$0.2$0.28k
Nous Capybara 7B V1.9$0.2$0.2
Nous Hermes 2 Mistral 7B$0.2$0.232k
Nous Hermes Llama 2 7B$0.2$0.2
OLMo 7B$0.2$0.2
OLMo 7B Twin-2T$0.2$0.2
OpenChat 3.5 (0106)$0.2$0.28k
OpenHermes 2 Mistral 7B$0.2$0.232k
OpenHermes 2.5 Mistral 7B$0.2$0.232k
Qwen1.5-7B$0.2$0.232k
Snorkel Mistral PairRM$0.2$0.232k
StripedHyena Hessian 7B$0.2$0.232k
StripedHyena Nous 7B$0.2$0.232k
Together AI Llama-3-8B-Instruct$0.2$0.28k
Toppy M 7B$0.2$0.24k
Vicuna 7B V1.5$0.2$0.22k
Llama 4 Maverick 17B Instruct FP8$0.27$0.851m
Chronos Hermes 13B V2$0.3$0.34k
CodeLlama 13B$0.3$0.3100k
CodeLlama 13B Python$0.3$0.3100k
Llama 2 13B Chat$0.3$0.34k
MiniMax M2.5$0.3$1.20197k
MythoMax L2 13B$0.3$0.34k
NexusRaven-V2 13B$0.3$0.3100k
Nous Hermes Llama 2 13B$0.3$0.3
ReMM SLERP L2 13B$0.3$0.34k
SOLAR 10.7B$0.3$0.34k
Together AI CodeLlama-34B-Instruct$0.3$0.3100k
Together AI Deepseek-Coder-33B-Instruct$0.3$0.316k
Together AI Yi-34B-Chat$0.3$0.34k
Vicuna 13B V1.5$0.3$0.32k
WizardLM 13B V1.0$0.3$0.32k
Gemma 4 31B IT$0.39$0.97256k
Mixtral 8x7B Instruct v0.1$0.4$0.433k
Together AI Nous-Hermes-2-Mixtral-8x7B-DPO$0.4$0.433k
Kimi K2.5$0.5$2.80256k
Together AI Llama-2-70B-chat$0.5$0.64k
DeepSeek V3$0.6$1.7064k
DeepSeek V3.1$0.6$1.7064k
Dolphin 2.5 Mixtral 8x7B$0.6$0.632k
Nous Hermes 2 Mixtral 8x7B$0.6$0.632k
Qwen3.5-397B-A17B$0.6$3.60262k
Together AI Deepseek-LLM-67B-Chat$0.6$0.64k
Together AI Llama-3-70B-Instruct$0.6$0.758k
Together AI Qwen2-72B-Instruct$0.7$0.733k
CodeLlama 34B$0.8$0.8100k
CodeLlama 34B Python$0.8$0.8100k
DeepSeek Coder 33B$0.8$0.816k
Nous Hermes 2 Yi 34B$0.8$0.8200k
Phind CodeLlama 34B V2$0.8$0.88k
Qwen1.5-32B$0.8$0.832k
WizardCoder Python 34B$0.8$0.8100k
Yi 34B$0.8$0.8200k
Llama 3 70B Instruct$0.88$0.888k
Llama 3.1 70B Instruct$0.88$0.88128k
CodeLlama 70B$0.9$0.916k
CodeLlama 70B Python$0.9$0.916k
DeepSeek 67B Chat$0.9$0.94k
Llama 2 70B Chat$0.9$0.94k
Platypus2 70B$0.9$0.9
Qwen1.5-72B$0.9$0.932k
Qwen2-72B$0.9$0.9128k
GLM-5$1.00$3.20200k
Together AI WizardLM-2-8x22B$1.00$1.5033k
Llama 3.3 70B Instruct (free)$1.04$1.0466k
DBRX Instruct$1.20$1.2032k
Kimi K2 Instruct$1.20$4.50131k
Kimi K2.6$1.20$4.50262k
Mixtral 8x22B v0.1$1.20$1.2064k
Qwen1.5-110B$1.80$1.8032k
Arctic$2.40$2.404k
DeepSeek R1$3.00$7.00128k
DeepSeek R1 0528$3.00$7.00130k
Llama 3.1 405B Instruct$5.00$15.00128k
Gemma 4 26B A4B IT256k
Llama 4 Scout 17B-16E Instruct10m

Where else to run this

Pricing Overview

Cheapest$0.02/1M
Most expensive$5.00/1M

About Together AI

Platform for running open-source and proprietary LLMs

Full provider profile →