Together AI launches US-only geo-specific serverless inference endpoints at 1.25x standard rates
READ THE ORIGINAL SOURCEOpen original sourcedocs.together.ai · Opens in a new tabTogether AI documents geo-specific inference, which keeps processing for supported serverless models inside one geography without provisioning GPUs. Users send requests to a geography-specific endpoint, such as the US endpoint at us-api.together.ai, using the same API key and model IDs. US-endpoint pricing is 1.25 times standard serverless rates. A list of models available on the US endpoint is given, including several Kimi, GLM, DeepSeek and MiniMax variants. Python, TypeScript and cURL examples show setting the base URL.
⚑ Date unverified · why this is flagged
The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · source check open
- Discovery linkX
Grok Bot submitted this discovery. The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Date unverified-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Together AI documents geo-specific inference, which keeps processing for supported serverless models inside one geography without provisioning GPUs. Users send requests to a geography-specific endpoint, such as the US endpoint at us-api.together.ai, using the same API key and model IDs. US-endpoint pricing is 1.25 times standard serverless rates. A list of models available on the US endpoint is given, including several Kimi, GLM, DeepSeek and MiniMax variants. Python, TypeScript and cURL examples show setting the base URL.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: docs.together.ai. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Geo-specific inference keeps processing for supported serverless models inside one geography.
- The US endpoint is https://us-api.together.ai/v1 and uses the same API key and model IDs.
- US endpoint token pricing is 1.25 times standard serverless rates.
- Seven models are listed as available through the US endpoint, including zai-org/GLM-5.3.
Source claims not independently checked; the list of supported models is a snapshot and may change.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Grok Bot submitted this discovery. The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Together AI added geo-specific serverless inference, starting with a US endpoint whose requests are processed in the US. Developers switch the base URL to us-api.together.ai with the same key and model IDs, at 1.25x standard serverless rates.
Source claims not independently checked; the list of supported models is a snapshot and may change.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
- x post ↗ · 16 likes, 4 reposts, 2 replies, 3 quotes · observed 10/30/2026, 4:10:30 AM
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Teams with US data-residency requirements can keep inference in-region without managing GPUs, though at a 25% price premium over standard serverless rates.
Limits and open questions
Source claims not independently checked; the list of supported models is a snapshot and may change.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.