Provider

Together AI API pricing

Every Together AI model statlyte tracks, with current list prices in USD per million tokens and the full record of what has changed.

Official pricing page · Docs

24
models tracked
$0
cheapest input — Ternary Bonsai 27B
$3
dearest input — Kimi K3

Current pricing

Model InputOutputCache readContext
Inkling
thinkingmachines/Inkling
$1$4.05 524,288
MiniMax M3
MiniMaxAI/MiniMax-M3
$0.3$1.2 524,288
Qwen3.7 Max
Qwen/Qwen3.7-Max
$1.25$3.75
Qwen3.6 Plus
Qwen/Qwen3.6-Plus
$0.5$3 1,000,000
Qwen3.5 9B
Qwen/Qwen3.5-9B
$0.17$0.25 262,144
Kimi K3
moonshotai/Kimi-K3
$3$15 1,000,000
Kimi K2.7 Code
moonshotai/Kimi-K2.7-Code
$0.95$4 262,144
Kimi K2.6
moonshotai/Kimi-K2.6
$1.2$4.5 262,144
GLM-5.2
zai-org/GLM-5.2
$1.4$4.4 262,144
GPT-OSS 120B
openai/gpt-oss-120b
$0.15$0.6 128,000
GPT-OSS 20B
openai/gpt-oss-20b
$0.05$0.2 128,000
DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Pro
$1.74$3.48 512,000
DeepSeek V4 Flash (0731)
deepseek-ai/DeepSeek-V4-Flash-0731
$0.14$0.28 1,000,000
Nemotron 3 Ultra 550B-A55B
nvidia/nemotron-3-ultra-550b-a55b
$0.6$3.6 512,300
Llama 3.3 70B Instruct Turbo
meta-llama/Llama-3.3-70B-Instruct-Turbo
$1.04$1.04 131,072
Qwen2.5 7B Instruct Turbo
Qwen/Qwen2.5-7B-Instruct-Turbo
$0.3$0.3 32,768
Gemma 4 31B IT
google/gemma-4-31B-it
$0.39$0.97 262,144
Qwen3.7 Plus
Qwen/Qwen3.7-Plus
$0.32$1.28 1,000,000
Gemma 3n E4B IT
google/gemma-3n-E4B-it
$0.06$0.12 32,768
LFM2.5 8B-A1B
LiquidAI/LFM2.5-8B-A1B
$0.03$0.12 32,768
Inkling Small
thinkingmachines/Inkling-Small
$0.5$1.2 524,288
Cogito v2.1 671B
deepcogito/cogito-v2-1-671b
$1.25$1.25 163,840
Gemma 4 31B Instruct (Pearl AI)
pearl-ai/gemma-4-31b-it
$0.28$0.86 32,000
Ternary Bonsai 27B
Prism-ML/Ternary-Bonsai-27B
$0$0 262,144

Recent changes at Together AI

Together AI launched Ternary Bonsai 27B
2026-08-07
Together AI launched Gemma 4 31B Instruct (Pearl AI)
2026-08-07
Together AI launched Cogito v2.1 671B
2026-08-07
Together AI launched Inkling Small
2026-08-07
LFM2.5 8B-A1B added to statlyte coverage
2026-08-07
Gemma 3n E4B IT added to statlyte coverage
2026-08-07
Qwen3.7 Plus added to statlyte coverage
2026-08-07
Gemma 4 31B IT added to statlyte coverage
2026-08-07
Qwen2.5 7B Instruct Turbo added to statlyte coverage
2026-08-07
Llama 3.3 70B Instruct Turbo added to statlyte coverage
2026-08-07
Nemotron 3 Ultra 550B-A55B added to statlyte coverage
2026-08-07
DeepSeek V4 Flash (0731) added to statlyte coverage
2026-08-07
DeepSeek V4 Pro added to statlyte coverage
2026-08-07
GPT-OSS 20B added to statlyte coverage
2026-08-07
GPT-OSS 120B added to statlyte coverage
2026-08-07
GLM-5.2 added to statlyte coverage
2026-08-07
Kimi K2.6 added to statlyte coverage
2026-08-07
Kimi K2.7 Code added to statlyte coverage
2026-08-07
Kimi K3 added to statlyte coverage
2026-08-07
Qwen3.5 9B added to statlyte coverage
2026-08-07