LimitWatch

Together AI · pricing · 2026-06-09 Backfilled

Together AI: DeepSeek-V4-Pro serverless price lowered; cached-input pricing added for GLM-5.1 and Qwen3.5-397B-A17B.

Old DeepSeek-V4-Pro $2.10 input / $4.40 output per 1M
New DeepSeek-V4-Pro $1.74 / $3.48; GLM-5.1 cached $0.26; Qwen3.5-397B cached $0.35 per 1M

Why it matters: If you use Together serverless (DeepSeek-V4-Pro, cached input), this changes its pricing. Effective 2026-06-09.

Alerts waitlist (not launched)

Email alerts ($9/mo) when a company changes pricing or limits. Not live yet; waitlist only.

Choose companies (optional) 0 selected

Joining sends nothing now; we keep your email only to tell you when alerts launch. Remove it any time: support@testedmcp.com. Stored by Netlify Forms. Privacy

ProductTogether serverless (DeepSeek-V4-Pro, cached input)
Categorypricing
Announced / detected2026-06-09 Backfilled
BackfilledYes: added retroactively
Quote verified againsthttps://docs.together.ai/docs/changelog
Effective2026-06-09
BeforeDeepSeek-V4-Pro $2.10 input / $4.40 output per 1M
AfterDeepSeek-V4-Pro $1.74 / $3.48; GLM-5.1 cached $0.26; Qwen3.5-397B cached $0.35 per 1M
Official sourcehttps://docs.together.ai/docs/changelog
Source quote
Input: $2.10 → $1.74. Output: $4.40 → $3.48.
ArchiveNo post-change Wayback capture found
Snapshot hashsha256:d1dce862e980e02793e6426f77fdf311c6c03dee3e8da144926ade901a6360c3
Statusverified

All Together AI changes · Dispute or correct this entry

Previous changes from Together AI

How Together AI limits and pricing work · All changes, June 2026