Skip to content
HomeTogether AIAll changesFour serverless inference models removed
Together AI
Product changeFeature removedOct 23 → Oct 26, 2026

Together AI: Four serverless inference models dropped from the pricing list: Gemma 4 31B, DeepSeek V4 Flash 0731, Llama…

Detected Oct 26, 2026AI & Machine Learning
The changeFour serverless inference models removed
BeforeOct 23Four serverless inference models
AfterOct 26Not listed
removed
1 change2 capturesOct 23, 2026 → Oct 26, 2026

What happened

Between the Oct 23, 2026 and Oct 26, 2026 captures of Together AI's pricing page, Pulse recorded one change: Four serverless inference models dropped from the pricing list: Gemma 4 31B, DeepSeek V4 Flash 0731, Llama 3.3 70B and MiniMax M2.7. Pulse files it as a product change (feature removed). Pulse's latest capture (Nov 16, 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 6 days after Together AI's previous change, "Together AI adds NVIDIA B200 post-training at $11/GPU/hr, $9 launch promo" (Oct 20, 2026). Before that Pulse recorded "Together AI ends free Muse Spark Open promo; $1.25/$4.25 pricing now applies" (Oct 19, 2026), "Together AI adds Reflection Beam to serverless at $0.40 per 1M input tokens" (Oct 17, 2026) and "Together AI makes Muse Spark Open free until Oct 18, adds Nemotron 3.5 Super VL" (Oct 16, 2026). Together AI has been tracked since 2025-12-23.

In the same window OpenAI, Huggingface, Google, Mistral AI and Anthropic also changed their AI & Machine Learning pricing pages. Those moves are listed further down, and the Pulse Agent can compare them side by side.

  • Serverless InferenceFeature
    Removed

    BeforeFour serverless inference models

    AfterNot listed

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 compared

Full-page captures of Together AI's pricing page (www.together.ai) from Oct 23, 2026 and Oct 26, 2026; the change is marked near the top of the page, where the Four serverless inference models no longer appears.

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
  1. Nov 8, 2026Price increaseTogether AI hikes Qwen3.7-Max to $2.50/$7.50, cuts six models, adds Kimi K3.1 Pro
  2. Nov 7, 2026Price increaseTogether AI raises Qwen3.7-Max inference prices 67%, drops four serverless models
  3. Nov 5, 2026ImprovementTogether AI adds Kimi K3.1 Pro at $2/$10 per 1M tokens, plus Ripple-65B Preview
  4. Oct 26, 2026Feature removedTogether AI: Four serverless inference models dropped from the pricing list: Gemma 4 31B, DeepSeek V4 Flash 0731, Llama… This change
  5. Oct 20, 2026PackagingTogether AI adds NVIDIA B200 post-training at $11/GPU/hr, $9 launch promo
  6. Oct 19, 2026PackagingTogether AI ends free Muse Spark Open promo; $1.25/$4.25 pricing now applies
  7. Oct 19, 2026ImprovementTogether AI lists Muse Spark Open, Reflection Beam, Nemotron 3.5 Super VL
  8. Oct 17, 2026ImprovementTogether AI adds Reflection Beam to serverless at $0.40 per 1M input tokens
  9. Oct 16, 2026PackagingTogether AI makes Muse Spark Open free until Oct 18, adds Nemotron 3.5 Super VL
  10. Oct 14, 2026Price increaseTogether AI ends Kimi K3 cached-input promo; price returns to $0.30/1M

Across AI & Machine Learning in the same window

All AI & Machine Learning changes
  1. OpenAIOct 26OpenAI rewrites Free, Go, Plus and Pro taglines in "Best for" format
  2. HuggingfaceOct 16Huggingface adds Nvidia RTX PRO 6000 GPUs to Spaces from $2.75/hr
  3. GoogleOct 12Google Workspace swaps Gems for AI skills, rewords Gemini on Starter plan
  4. Mistral AIOct 12Mistral AI cuts Free plan API credits, gives free users Vibe CLI and IDE tools
  5. AnthropicOct 12Anthropic API launches Haiku 5.5 at $0.10/$0.50 per MTok, Haiku 4.5 goes Legacy

Questions about this change

Did Together AI raise prices in October 2026?

No list-price increase was recorded between Oct 23, 2026 and Oct 26, 2026. The change Pulse detected was a product change: feature removed.

What changed on Together AI's pricing page between Oct 23, 2026 and Oct 26, 2026?

Serverless Inference feature removed: Four serverless inference models. Pulse compared the captures it took on Oct 23, 2026 and Oct 26, 2026; the before/after table above lists each item as written on the page.

How often does Together AI change its pricing?

Pulse recorded 19 other pricing-page changes for Together AI in the 90 days before this one; the previous change was "Together AI adds NVIDIA B200 post-training at $11/GPU/hr, $9 launch promo" on Oct 20, 2026; Together AI has been tracked since 2025-12-23.