What is the cheapest Together model?

gpt-oss-120B is currently Together's cheapest paid tracked model at $0.15 per 1M input tokens and $0.6 per 1M output tokens.

How many Together models are tracked?

10 current Together models are tracked, each linked to the official pricing page. The dataset is refreshed twice daily.

Does Together offer cached-input pricing?

Together lists cached-input (prompt-caching) prices for 6 tracked models — cached input is billed at a discount when a prompt prefix repeats.

Together

Hosting provider · 10 models tracked · Founded 2022

Inference platform hosting 200+ open-source models with simple per-token pricing. Strong coverage of Qwen, GLM, Kimi, MiniMax, and DeepSeek variants.

Together pricing at a glanceAugust 2026 · $ per 1M tokens

Together API pricing (August 2026): 10 current models range from $0.150 to $1.74 per 1M input tokens and $0.600 to $4.40 per 1M output tokens. The cheapest paid model is gpt-oss-120B at $0.150/1M input; the priciest is DeepSeek V4 Pro at $1.74/1M input / $3.48 output. Every price links to Together's official pricing page and refreshes twice daily.

Models10

Input range$0.150–$1.74

Output range$0.600–$4.40

Cached-input tiers6

Today's Together prices

10 models · cheapest blended first

Sorted by blended cost (cheapest first). Prices per 1M tokens, August 2026 — every price links to Together's official pricing page.

Current Together model prices per 1M tokens, sorted by blended cost
Model	Blended*	Input	Output	Cached in	Context	Status
gpt-oss-120B	$0.262	$0.150	$0.600	—	128K	Current
Gemma-4-31B-it-Pearl	$0.425	$0.280	$0.860	—	128K	Current
MiniMax M3	$0.525	$0.300	$1.20	$0.060	1M	Current
Qwen3.7-Plus	$0.560	$0.320	$1.28	—	128K	Current
Llama 3.3 70B	$1.04	$1.04	$1.04	—	128K	Current
NVIDIA Nemotron 3 Ultra	$1.35	$0.600	$3.60	$0.200	128K	Current
Kimi K2.7 Code	$1.71	$0.950	$4.00	$0.190	256K	Current
Qwen3.7-Max	$1.88	$1.25	$3.75	$0.130	1M	Current
GLM-5.2	$2.15	$1.40	$4.40	$0.260	1M	Current
DeepSeek V4 Pro	$2.17	$1.74	$3.48	$0.200	1M	Current