Skip to content

Together AI

Inference host · 12 models · 12 priced routes · together.ai

Models on Together AI

ModelIn / out per 1M
DeepSeek V4 Flash 0731
Together AI
$0.14 / $0.28+121% vs headline
Qwen3.5-9B
Together AI
$0.17 / $0.25+105% vs headline
GLM 5.3 Flash
Together AI
$0.15 / $0.5+245% vs headline
gpt-oss-120b
Together AI
$0.15 / $0.6+304% vs headline
DeepSeek V4.1 Flash
Together AI
$0.3 / $1.2+100% vs headline
Muse Glimmer 30B
Together AI
$0.35 / $1.5+27% vs headline
Llama 3.3 70B Instruct
Together AI
$1.04 / $1.04+571% vs headline
DeepSeek V4 Pro 0813
Together AI
$1.32 / $3.96+100% vs headline
GLM 5.3
Together AI
$1.4 / $4.4+149% vs headline
GLM 5.2
Together AI
$1.4 / $4.4+149% vs headline
Qwen3.8 2.4T A95B
Together AI
$2 / $6Same vs headline
Kimi K3
Together AI
$3 / $15+82% vs headline

About Together AI

Cloud platform for training, fine-tuning and serving open-source AI models.

Batch: Run asynchronous batch workloads at up to 50% lower cost (docs.together.ai batch-inference); only selected serverless models get 50% off

Caching: Cached input prices listed per model in tables (e.g. $0.30 input, $0.06 cached)

Across fru.devCompany profileSeries C, $800M (2026-07)

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.