Skip to content
HomeTogether AIAll changesTwo new models added
Together AIProduct change · Feature added · Jul 16 → Jul 17, 2026

Together AI: Added Inkling & LFM2.5-8B-A1B models to Serverless Inference

Verified Jul 17, 2026AI & Machine LearningDirection: up
The changeTwo new models — added.
Before · Jul 16No Two new models
After · Jul 17Two new models
added
1 change2 capturesJul 16, 2026 → Jul 17, 2026

What happened

Between the Jul 16, 2026 and Jul 17, 2026 captures of Together AI's pricing page, Pulse recorded one change: Two new models added to Serverless Inference catalog — Inkling ($1.20/1M input, $4.05/1M output, $0.17 cached) and LFM2.5-8B-A1B ($0.03/1M input, $0.12/1M output). In detail: Two new models added to the Serverless Inference catalog: Inkling ($1.20/1M input, $4.05/1M output, $0.17 cached) and LFM2.5-8B-A1B ($0.03/1M input, $0.12/1M output). Pulse files it as a product change (feature added) with an upward direction. Pulse's latest capture (Oct 21, 2026) lists Managed Storage at $0.16 per GiB/month, Provisioned Throughput at $0.05 per PTU/minute, Sandbox (Code Interpreter) at $0.03 per session (60 min), GPU Clusters (On-demand) at $3.99 per hour (H100) and GPU Clusters (Reserved) at $3.69 per hour (H100, 3-30 days).

It lands 4 days after Together AI's previous change, "Together AI: New Provisioned Throughput pricing + GPU rate cuts" (Jul 13, 2026). Before that Pulse recorded "Together AI drops GLM-5 from serverless inference pricing" (Jun 30, 2026), "Together AI: new flagship models added, Llama 4 Maverick + Kimi K2.5 removed" (Jul 4, 2026) and "Together AI slashes GPU and AI inference prices up to 25%" (Jun 22, 2026). Together AI has been tracked since 2025-12-23.

In the same window Google, Anthropic, Huggingface, Mistral AI 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.

  • Serverless Inference · FeatureAdded
    No Two new modelsTwo new models

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 Jul 16, 2026 and Jul 17, 2026; the change is marked near the top of the page, where Two new models now 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. Jul 21, 2026packagingTogether AI: LFM2.5-8B-A1B model discontinued from Serverless Inference
  2. Jul 20, 2026improvedTogether AI: 3 new models added to Serverless Inference pricing
  3. Jul 18, 2026decreaseTogether AI: Inkling model price drop ($1.20→$1.00)
  4. Jul 17, 2026improvedTogether AI: Added Inkling & LFM2.5-8B-A1B models to Serverless Inference · this change
  5. Jul 13, 2026packagingTogether AI: New Provisioned Throughput pricing + GPU rate cuts
  6. Jun 30, 2026packagingTogether AI drops GLM-5 from serverless inference pricing
  7. Jul 4, 2026packagingTogether AI: new flagship models added, Llama 4 Maverick + Kimi K2.5 removed
  8. Jun 22, 2026decreaseTogether AI slashes GPU and AI inference prices up to 25%
  9. Jun 19, 2026packagingTogether AI reveals cached input pricing for GLM-5.1 and Qwen3.5
  10. Jun 10, 2026improvedTogether AI raises serverless inference prices across Llama, Qwen models

Across AI & Machine Learning in the same window

All AI & Machine Learning changes
  1. GoogleJul 6Google Vertexai delays Agent Gateway billing to July 13, extends free window
  2. AnthropicJul 6Anthropic launches Sonnet 5, cuts price to $2/$10 per MTok through Aug 31
  3. HuggingfaceJul 3Enterprise SCIM provisioning & Team SSO OIDC added + 2 more changes
  4. Mistral AIJun 2Mistral AI adds Task scheduling, Skills, and Workflows in major overhaul
  5. OpenAIMay 11OpenAI API raises GPT-Realtime-2 text output 50%, adds translate

Questions about this change

Did Together AI raise prices in July 2026?

No list-price increase was recorded between Jul 16, 2026 and Jul 17, 2026. The change Pulse detected was a product change: feature added.

What changed on Together AI's pricing page between Jul 16, 2026 and Jul 17, 2026?

Serverless Inference feature: No Two new models → Two new models, added. Pulse compared the captures it took on Jul 16, 2026 and Jul 17, 2026; the before/after table above lists each item as written on the page.

How often does Together AI change its pricing?

Pulse recorded 9 other pricing-page changes for Together AI in the 90 days before this one; the previous change was "Together AI: New Provisioned Throughput pricing + GPU rate cuts" on Jul 13, 2026; Together AI has been tracked since 2025-12-23.