Changelog

Route to Claude Sonnet 5.5, gpt-6.1-sol, and four more models

Three of the six run with zero data retention.

• Claude Sonnet 5.5 by Anthropic
• Claude Opus 5.5 through Amazon Bedrock, with zero data retention
• gpt-6.1-sol and gpt-live-1 by OpenAI, both with zero data retention
• mimo-v2.6-flash and mimo-v2.6-pro by Xiaomi Mimo

Read more in the Gateway model catalog docs.

OpenAI's ultrafast service tier is available on every Gateway API surface

Ultrafast is OpenAI's fastest processing tier and bills at six times the standard rate. Request it from any surface, alongside the flex and priority tiers. Read more in the Gateway service tiers docs.

previous_response_id chains on /v1/responses resume for 30 days

A stored turn stays available for 30 days, matching OpenAI's expiry, so a conversation picks up after a long pause. DELETE /v1/responses/{id} ends a chain early. Read more in the Gateway multi-turn conversations docs.

Gateway adds OpenAI audio translations, input token counting, and video management

Four more OpenAI endpoints pass through Gateway:

• Audio translations
• Responses input items
• Responses input token counting
• Video listing and deletion

Read more in the Gateway API reference docs.

Adobe Workfront, Tavily, WhatsApp Business, and nine more connectors join the catalog

Adobe Experience Manager (Cloud Service), Adobe Workfront, Alpha Vantage, Checkly, ConfigCat, Jamf Pro, Kit, Salesforce Data 360, Salesforce Marketing Cloud, Tavily, TinyPNG, and WhatsApp Business Cloud API are live. Jamf Pro responses include each device's OS and management state. Read more in the Agent Handler connectors docs.

Agent Handler adds Google sign-in and keeps SCIM roles in sync with your identity provider

Dashboard roles for SCIM-provisioned users are locked, so they always match the identity provider.

• A warning appears before a SCIM role mapping or role change would leave the organization without an Admin
• Identity provider checklists include Merge Admins and optional SSO setup steps
• The Agent Handler sign-in page offers single sign-on with Google

Change roles for SCIM-provisioned users in your identity provider. Read more in the Agent Handler SCIM provisioning docs

GET /remote-field-classes returns the selectable picklist and enum values for NetSuite custom fields and custom segments.

• Custom field types and formats normalize to one consistent set of values across Accounting
• POST /invoices and POST /expenses write relationship-type custom field values
• POST /invoices accepts both the previous and current custom field value formats

Read more in the NetSuite Accounting docs.

Batch inference runs through /v1/batches, with a Batches page in the dashboard

Submit chat completions, embeddings, responses, or Anthropic Messages requests as one provider batch, and results stream back as NDJSON. The Batches page sits next to Logs, filters by status and date, and opens a detail drawer with each batch's progress, cost, errors, and metadata. Read more in the batch inference docs.

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and grok-4.7 are available with zero data retention

Seven models are new in the catalog, including two text-to-speech models billed by the second.

• Claude Opus 5.5 by Anthropic, GPT-6 Sol and GPT-6 Luna by OpenAI, and grok-4.7 by xAI, each with zero data retention
• GLM-5.3 FlashX by Z.AI
• Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS by Google, billed per second of generated audio and reported in the X-Merge-Billed-Audio-Seconds header

Read more in the Gateway model catalog docs.

Guardrails and data controls take per-customer and per-project overrides

A customer's Configuration tab sets its own prompt injection and data loss prevention policy, which inherits the organization policy until overridden and is enforced at request time. A new Controls tab on projects and customers overrides zero data retention, vendor restrictions, and region restrictions, and each unit resets to the organization setting on its own. Read more in the per-customer restrictions docs.

Routing policies set reasoning effort and accept an inline priority_order

Reasoning effort takes a policy-wide default, minimum, and maximum, plus per-model overrides, all enforced at dispatch and factored into vendor choice. Pass priority_order on /v1/responses or any compatible surface to route through an ordered model list, and Gateway saves it as a visible routing policy. Read more in the routing policy docs.

/v1/responses breaks down latency per request

Transfer, gateway, and provider time come back in the response body and the streaming done chunk. Non-streaming calls also carry a Server-Timing header. Read more in the Responses API docs.

Real-time voice sessions run over WebSocket at /v1/live/sessions

Each session is backed by gpt-live-1 by OpenAI. Sessions run with zero data retention. Read more in the live voice docs.

Agent Handler adds Power BI, Dealops, and GCC High versions of Outlook and Excel

Four connectors cover analytics, quoting, and the US Government sovereign cloud.

• Microsoft Power BI: 42 tools across workspaces, reports, semantic models, dashboards, dataflows, gateways, and tenant administration
• Dealops: read the CPQ catalog, build and price quotes, and follow them through approval
• Outlook GCC High and Excel GCC High: for teams on the US Government sovereign cloud

Read more in the Agent Handler connectors docs.

Admins set connector tool access per user from the dashboard

Grant a user access to a connector's tools, edit that selection later, or revoke it, one user at a time. The Group access dialog adds search boxes and consolidates tool selection into a single shared list. Read more in the managing tool access docs.

Access keys take explicit scopes at creation

Pick scopes when you create an access key. Privileged keys carry a badge in the dashboard, with revoke actions that reflect their elevated access. Read more in the access keys docs.

Link's OAuth step and success screen become configurable per organization

An optional "Powered by Merge" mark can appear on the Link OAuth step. Organizations can also skip the success screen, so the flow closes as soon as a connector authorizes. Read more in the Link customization docs.

Accounting

The invoice creation schema describes each line item as an expanded object. If your integration reads line-item structure from this endpoint, confirm your parser handles the object form. Read more in the invoices meta docs.

An agent can create and hand off its own organization

mgw agent signup creates a sandboxed organization and returns a claim link. A human opens that link and claims the organization from the dashboard.

Guardrails verdicts surface in the API Tester and on the API

Prompt injection and DLP results attach to each request, in the dashboard and in the response body.

• The API Tester shows prompt injection and DLP results for each test request
• include_guardrails_metadata returns the same verdicts alongside a live response
• The flag covers /v1/responses and every SDK-compatible endpoint

Read more in the prompt injection protection docs.

Eight models arrive in the catalog with zero data retention

Sakana AI, OpenAI, and augure models land alongside GLM-5.3 Flash on three inference providers.

• Fugu Max and Fugu Ultra 2.0 from Sakana AI
• GPT Image 2.5 Flare and GPT Image 2.5 Sunburst from OpenAI for image generation
• ossington-5, rosedale-1, and tofino-3 from augure
• GLM-5.3 Flash through Fireworks AI, Modal, and Together AI

Read more in the model catalog docs.

POST /v1/images/edits edits images with reference images and masks

The endpoint takes a source image, optional reference images, and a mask. It runs on the token-billed image models.

The Performance tab reports prompt caching hit rate and savings

Cache hit rate, cached token counts, and estimated savings sit in a prompt caching section under Usage and spend.

Copper CRM, Dynamics 365 Business Central, Browserbase, and Discord are live

Four connectors this week, adding 66 tools on Copper CRM alone.

• Copper CRM: 66 tools with API key authentication
• Microsoft Dynamics 365 Business Central: purchases, general ledger, and generic record access
• Browserbase: cloud browser sessions, page fetch, web search, and autonomous agents
• Discord: messaging, channels and threads, roles, and moderation

Read more in the connector docs for the full tool list.

Microsoft OAuth connectors authenticate with a client certificate

Every Microsoft OAuth connector accepts a client certificate in place of a shared secret. Tenants whose app registrations mandate certificate authentication can complete a connection.

Warp and AgileATS are live across HRIS and ATS

ATS and HRIS

Four endpoints each, covering the employee record on one side and the hiring pipeline on the other.

• Warp: GET /employees, GET /employments, and GET /locations for the core employee record
• Warp: GET /employee-payroll-runs for deductions, earnings, and tax detail per run
• AgileATS: GET /jobs and GET /job-postings for open roles and the listings candidates see
• AgileATS: GET /applications and GET /job-interview-stages for submissions and pipeline steps

Read more in the Employees docs.

QuickBooks Online and Sage Intacct gain write endpoints

Accounting

POST /expenses creates expenses on QuickBooks Online, and POST /invoices creates invoices on Sage Intacct. QuickBooks Online expense creation uses an updated request structure. Read more in the Expenses docs.

Jira tickets accept native status and priority values

Ticketing

Set a Jira ticket's status and priority with Jira's own values, and a custom workflow configuration maps straight through.

• PATCH /tickets has the ability to set native status and priority
• POST /tickets has the ability to set native priority
• Inbound Jira webhooks carry native status values into PATCH /tickets

Read more in the Tickets docs.

The dashboard audit trail records end user and credential changes

Scope and selective sync filter changes made in Merge Link are attributed to the end user who made them. Partner credential updates record who changed them and when.

Gateway adds GPT-6 Astra, DeepSeek V4.1 Flash, and GLM-5.3 Flash

New

Nine models are routable today across text, image, and video. Read more in the Gateway model catalog docs.

• GPT-6 Astra by OpenAI, with zero data retention
• DeepSeek V4.1 Flash by DeepSeek, plus GLM-5.3 Flash through Fireworks AI and Together AI
• GPT Image 2.5 Flare and GPT Image 2.5 Sunburst for image generation, with zero data retention
• Seedance 2.5 Text to Video, Image to Video, and Reference to Video
• Fal.ai and Interfaze added as model vendors, Interfaze with its own zero-data-retention model

Model Explorer's detail pages compare vendors side by side

New

Each model's page sorts per-vendor pricing for input, output, and cache read rates, with promo discounts shown against the list price. Zero-data-retention labels, listed capabilities, and release dates sit on the same page, so picking a vendor for a given model takes one view.