Together AI pricing and rate-limit changes, May 2026
2 dated changes to Together AI (Together API) recorded in May 2026, 2026-05-14 to 2026-05-29. Each links the official source. This page lists changes, not Together AI's current limit tables.
Pricing
| Date | Change | Source | Status |
|---|---|---|---|
| 2026-05-29 Backfilled | Serverless prices increased for Qwen3.5-9B, Meta-Llama-3-8B-Instruct-Lite and Llama-3.3-70B-Instruct-Turbo.Old: Qwen3.5-9B $0.10/$0.15; Llama-3-8B-Lite $0.10/$0.10; Llama-3.3-70B-Turbo $0.88/$0.88 per 1M (in/out)New: Qwen3.5-9B $0.17/$0.25; Llama-3-8B-Lite $0.14/$0.14; Llama-3.3-70B-Turbo $1.04/$1.04 per 1M (in/out) | source · current price | verified |
| 2026-05-14 Backfilled | Announced price increase for google/gemma-4-31b-it effective 2026-05-21.$0.20 → $0.39 · $0.50 → $0.97Old: $0.20 input / $0.50 output per 1MNew: $0.39 input / $0.97 output per 1M | source · current price | verified |
FAQ
Did Together AI change its pricing in May 2026?
Yes, 2 recorded changes. 2026-05-29: Serverless prices increased for Qwen3.5-9B, Meta-Llama-3-8B-Instruct-Lite and Llama-3.3-70B-Instruct-Turbo. Source: https://docs.together.ai/docs/changelog (entry). 2026-05-14: Announced price increase for google/gemma-4-31b-it effective 2026-05-21. Source: https://docs.together.ai/docs/changelog (entry).
All Together AI changes · All companies, May 2026 · Methodology