Together AI cuts Qwen3 inference prices 50%, adds caching
What happened
Between the May 25, 2026 and Jun 1, 2026 captures of Together AI's pricing page, Pulse recorded one change: Qwen3.7-Max serverless inference pricing decreased: input from $2.50 to $1.25/1M tokens (50% cut), output from $7.50 to $3.75/1M tokens (50% cut); new cached input price of $0.13/1M tokens added. Pulse files it as a pricing change (price decrease) with a downward direction. Pulse's latest capture (Nov 15, 2026) lists Provisioned Throughput at $0.05 per PTU/minute, GPU Clusters (On-demand) at $3.99 per hour (H100), GPU Clusters (Reserved) at $3.69 per hour (H100, 3-30 days), Sandbox (Code Sandbox) at $0.04 per vCPU/hour + $0.01 per GiB RAM/hour and Serverless Inference at $0.15 per 1M input tokens.
It lands 3 days after Together AI's previous change, "Together AI reveals H200 GPU rates and adds Qwen3.7-Max inference" (May 29, 2026). Before that Pulse recorded "Together AI Triples Gemma 3n E4B Pricing to $0.06/$0.12 per 1M Tokens" (Apr 24, 2026), "Together AI adds 11 models including Gemma 4 and raises GLM-5 prices up to 40%" (Apr 13, 2026) and "Together AI hikes reserved GPU rates up to 30% and drops three AI models" (Apr 9, 2026). Together AI has been tracked since 2025-12-23.
In the same window Anthropic, Mistral AI, Huggingface, Google and OpenAI also changed their AI & Machine Learning pricing pages. Those moves are listed further down, and the Pulse Agent can compare them side by side.
- −50%Serverless InferencePrice$2.50$1.25
| Plan | Field | Before | After | Change |
|---|---|---|---|---|
| Serverless Inference | Price | $2.50 | $1.25 | −50% |
Values as written on Together AI's public pricing page in the two captures Pulse compared; where the page states no number, the cells give the wording before and after.
Evidence
The two captures Pulse comparedFull-page captures of Together AI's pricing page (www.together.ai) from May 25, 2026 and Jun 1, 2026; the change is marked near the top of the page, where serverless inference price reads $2.50 and then $1.25.
Sign in to see the evidence
The two full-page captures with this change marked up are free with an account.
Together AI, the last 90 days
Full history- Jun 22, 2026Price decreaseTogether AI slashes GPU and AI inference prices up to 25%
- Jun 18, 2026PackagingTogether AI reveals cached input pricing for GLM-5.1 and Qwen3.5
- Jun 9, 2026Price increaseTogether AI raises serverless inference prices across Llama, Qwen models
- Jun 2, 2026Price decreaseTogether AI cuts Qwen3 inference prices 50%, adds caching This change
- May 29, 2026PackagingTogether AI reveals H200 GPU rates and adds Qwen3.7-Max inference
- Apr 24, 2026Price increaseTogether AI Triples Gemma 3n E4B Pricing to $0.06/$0.12 per 1M Tokens
- Apr 13, 2026ImprovementTogether AI adds 11 models including Gemma 4 and raises GLM-5 prices up to 40%
- Apr 9, 2026Price increaseTogether AI hikes reserved GPU rates up to 30% and drops three AI models
- Apr 3, 2026Price increaseTogether AI Raises GPU Prices Up to 36% and Restructures Cloud Tiers
- Apr 1, 2026PackagingTogether AI Drops Pricing for Qwen3, Sora 2 Pro, and Kimi K2 Models
Across AI & Machine Learning in the same window
All AI & Machine Learning changes- AnthropicJun 2Anthropic API launches Opus 4.8 with new fast mode for lightning speeds
- Mistral AIJun 2Mistral AI adds Task scheduling, Skills, and Workflows in major overhaul
- HuggingfaceJun 1Huggingface upgrades free GPUs to RTX Pro 6000 with 96GB VRAM
- GoogleMay 26Google Cloud renames Vertex AI Search to Agent Search for commerce
- OpenAIMay 11OpenAI API raises GPT-Realtime-2 text output 50%, adds translate
Questions about this change
Did Together AI raise prices in June 2026?
No — prices went down. Between May 25, 2026 and Jun 1, 2026 Together AI's pricing page showed 1 price cut: Serverless Inference: $2.50 → $1.25 (−50%).
What changed on Together AI's pricing page between May 25, 2026 and Jun 1, 2026?
Serverless Inference price: $2.50 → $1.25 (−50%). Pulse compared the captures it took on May 25, 2026 and Jun 1, 2026; the before/after table above lists each item as written on the page.
How often does Together AI change its pricing?
Pulse recorded 7 other pricing-page changes for Together AI in the 90 days before this one; the previous change was "Together AI reveals H200 GPU rates and adds Qwen3.7-Max inference" on May 29, 2026; Together AI has been tracked since 2025-12-23.