Releasesby GlyphProjects is now generally available Projects is out of private preview and available to all organizations
Projects is now generally available Projects is out of private preview and available to all organizations. Use Projects to group API keys, set per-project rate limits, segment usage analytics, and manage member access across isolated workspaces. Every organization starts with a Default Project, so existing setups are unchanged.
Also shipped May 1, 2026Cerebras in May 2026 →
New Audio APIs for Speech and Transcription
OpenRouter launched two new endpoints for audio transcription and speech synthesis. These APIs provide access to multiple providers under a single interface.
Postgres 18 GA, organization spending limits API, US East NAT gateway and PrivateLink updates, plv8 deprecated, k6 load testing release - May 01, 2026
Postgres 18 is generally available. Postgres 18 is now generally available on Neon. The preview limitations have been lifted, and Postgres 18 is fully supported...
What's new in Sigma
Admin Connection-level OAuth for Snowflake and Databricks (GA) Set up a specific OAuth configuration to authenticate to a Snowflake or Databricks connection without reusing the OAuth configuration used to authenticate to your Sigma organization.
- Streamlined Dives sidebar: The Dives list in the Object Explorer is now capped at your 10 most recent...
- Streamlined Dives sidebar: The Dives list in the Object Explorer is now capped at your 10 most recent Dives, with a new View all Dives link that opens the full searchable Dives table.
Cog 0.19.2
Changelog 427d486 Bump version to 0.19.2 ( #2984 ) d9c2b14 fix: cap fuzz test input size to prevent timeout ( #2981 ) 4269575 fix: support typing_extensions TypedDict at runtime ( #2983 )
Diffusers 0.38.0: New image and audio pipelines, Core library improvements, and more
New Pipelines LLaDA2 LLaDA2 is a family of discrete diffusion language models that generate text through block-wise iterative refinement. Instead of autoregressive token-by-token generation, LLaDA2 starts with a fully masked sequence and progressively unmasks tokens by confidence over multiple refinement steps.
More from Cerebras InferenceEvery Cerebras Inference release →
New dedicated models: GLM 5, GLM 5.1, and Kimi K2.6 Z.AI's GLM 5 and GLM 5.1 and Moonshot AI's Kimi K2.6 are...
New dedicated models: GLM 5, GLM 5.1, and Kimi K2.6 Z.AI's GLM 5 and GLM 5.1 and Moonshot AI's Kimi K2.6 are now supported on Dedicated Endpoints.
Validation Errors Now Return 400 Instead of 422 API requests that fail validation now return HTTP 400 Bad...
Validation Errors Now Return 400 Instead of 422 API requests that fail validation now return HTTP 400 Bad Request instead of 422 Unprocessable Entity, aligning the HTTP status code with standard behavior across major inference providers.
New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional...
New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional prompt_cache_key parameter. Requests that share the same key are routed together so they reuse the same prompt cache, increasing cache hits and reducing time to first token.
Payload Optimization: msgpack and gzip /v1/chat/completions and /v1/completions now accept request bodies...
Payload Optimization: msgpack and gzip /v1/chat/completions and /v1/completions now accept request bodies encoded with msgpack (Content-Type: application/vnd.msgpack) and/or compressed with gzip (Content-Encoding: gzip). This can significantly reduce payload size and improve TTFT for requests with long prompts.
New dedicated models: StepFun Step 3.5 Flash and Step 3.7 Flash StepFun's Step 3.5 Flash and Step 3.7 Flash...
New dedicated models: StepFun Step 3.5 Flash and Step 3.7 Flash StepFun's Step 3.5 Flash and Step 3.7 Flash are now supported on Dedicated Endpoints.
New Sampling Parameters The following parameters are now available on all models: - frequency_penalty –...
New Sampling Parameters The following parameters are now available on all models: frequency_penalty – Reduces repetition by penalizing tokens based on how often they have appeared so far presence_penalty – Reduces repetition by penalizing tokens that have appeared at least once logit_bias – Adjusts the likelihood of specific tokens appearing in the response
Streaming: Server-Sent Events (SSE) Streaming responses for Chat Completions (/v1/chat/completions) and...
Streaming: Server-Sent Events (SSE) Streaming responses for Chat Completions (/v1/chat/completions) and Completions (/v1/completions) now emit a standard data: [DONE] SSE event at the end of the stream, following the SSE standard (see the living specification). The [DONE] marker is guaranteed to appear exactly once and is always the last event in the stream.
Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers...
Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers while preserving full precision for sensitive layers, in line with industry standards. Learn more in Supported Models.