Together AI: Announced price increase for google/gemma-4-31b-it effective 2026-05-21.
$0.20 → $0.39 · $0.50 → $0.97
Old $0.20 input / $0.50 output per 1M
New $0.39 input / $0.97 output per 1M
Why it matters: If you use Together serverless (gemma-4-31b-it), this changes its pricing. Effective 2026-05-21.
Alerts waitlist (not launched)
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
| Product | Together serverless (gemma-4-31b-it) |
|---|---|
| Category | pricing |
| Announced / detected | 2026-05-14 Backfilled |
| Backfilled | Yes: added retroactively |
| Quote verified against | https://docs.together.ai/docs/changelog |
| Effective | 2026-05-21 |
| Before | $0.20 input / $0.50 output per 1M |
| After | $0.39 input / $0.97 output per 1M |
| Official source | https://docs.together.ai/docs/changelog |
| Source quote | $0.20 → $0.39 (input), $0.50 → $0.97 (output) per 1M tokens. |
| Archive | No post-change Wayback capture found |
| Snapshot hash | sha256:d1dce862e980e02793e6426f77fdf311c6c03dee3e8da144926ade901a6360c3 |
| Status | verified |
All Together AI changes · Dispute or correct this entry
Previous changes from Together AI
- 2026-10-02: Dynamic serverless rate limits that scaled with recent traffic were retired.
- 2026-09-22: Serverless prices lowered for Qwen3.7-Max and Qwen3.8-Flash.
- 2026-06-09 Backfilled: DeepSeek-V4-Pro serverless price lowered; cached-input pricing added for GLM-5.1 and Qwen3.5-397B-A17B.
- 2026-05-29 Backfilled: Serverless prices increased for Qwen3.5-9B, Meta-Llama-3-8B-Instruct-Lite and Llama-3.3-70B-Instruct-Turbo.
- 2026-04-24 Backfilled: Billable training tokens for no-packing fine-tuning jobs now calculated as len(dataset) * max_seq_length.
- 2026-04-22 Backfilled: Build Tiers 1-5, Scale and Enterprise tier labels retired, dynamic rate limits enabled for all users, billing moved to fully prepaid.
- 2026-04-15 Backfilled: Serverless price increased for google/gemma-3n-E4B-it.
How Together AI limits and pricing work · Together AI changes, May 2026