Releasesby GlyphNew Default Concurrency Limits
We're increasing default concurrency limits by up to 3X for Streaming Speech to Text , Text to Speech , and Voice Agent for Pay as you Go, Growth, and Enterprise plans. For full details on the rate limits for your plan, see the API Rate Limits documentation.
Also shipped Feb 11, 2026Deepgram in February 2026 →
Support for osonly24 runtime is in General Availability
Support for osonly24 runtime is in General Availability . The OS only runtime lets you deploy binaries such as Dart and Go. For more information, see Configure the OS only runtime .
Cloudflare One Appliance, Cloudflare One, Cloudflare WAN - Post-quantum encryption support for Cloudflare One Appliance
Cloudflare One Appliance version 2026.2.0 adds post-quantum encryption support using hybrid ML-KEM (Module-Lattice-Based Key-Encapsulation Mechanism). The appliance now uses TLS 1.3 with hybrid ML-KEM for its connection to the Cloudflare edge.
Workers are no longer limited to 1000 subrequests
Workers no longer have a limit of 1000 subrequests per invocation, allowing you to make more fetch() calls or requests to Cloudflare services on every incoming request. This is especially important for long-running Workers requests, such as open websockets on Durable Objects or long-running Workflows , as these could often exceed this limit and error.
Workers - Improved React Server Components support in the Cloudflare Vite plugin
The Cloudflare Vite plugin now integrates seamlessly @vitejs/plugin-rsc ↗ , the official Vite plugin for React Server Components ↗ . A childEnvironments option has been added to the plugin config to enable using multiple environments within a single Worker.
Diversity sampling for Adaptive Traces
Easily and confidently optimize trace storage while ensuring even your smallest sets of traces are represented. Diversity sampling captures at least one trace for each unique trace combination (fingerprint) within a fixed time window. These combinations are defined by attributes such as service, route, and status code.
More from DeepgramEvery Deepgram release →
Container Images (release 260212)
- quay.io/deepgram/self-hosted-api:release-260212 Equivalent image to: quay.io/deepgram/self-hosted-api:1.177.3 quay.io/deepgram/self-hosted-engine:release-260212 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.107.0-1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260212 Equivalent image...
This Release Contains The Following Changes
- General Improvements , Keeps our software up-to-date.
🤖 New OpenAI & Gemini LLM Models Support
We've added support for new LLM models in our Voice Agent API! Available Models: OpenAI GPT 5.2 Instant (gpt-5.2-instant) OpenAI GPT 5.2 Thinking (gpt-5.2) Google Gemini 3 Flash (gemini-3-flash-preview) Implementation: Configure your chosen model in your Voice Agent settings: { "type": "Settings", "agent": { "think": { "provider": { "type": "open_ai"...
Nova-3 Multilingual Model Update
🌍 Nova-3 Multilingual Improvements We’ve released an updated Nova-3 multilingual model , delivering accuracy improvements across supported languages , with the largest gains in code-switching scenarios .
Nova-3 Model Update
🌐 Nova-3 Adds Support for Hebrew, Farsi, and Urdu We're excited to announce the release of new Nova-3 monolingual models for Hebrew , Farsi , and Urdu ! These additions bring industry-leading speech-to-text capabilities for users of these languages.
Container Images (release 260129)
- quay.io/deepgram/self-hosted-api:release-260129 Equivalent image to: quay.io/deepgram/self-hosted-api:1.177.3 quay.io/deepgram/self-hosted-engine:release-260129 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.107.0-1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260129 Equivalent image...
This Release Contains The Following Changes
- Nova-3 Supports 12 New Languages , Belarusian (be), Bengali (bn), Bosnian (bs), Croatian (hr), Kannada (kn), Macedonian (mk), Marathi (mr), Serbian (sr), Slovenian (sl), Tamil (ta), Tagalog (tl), and Telugu (te). Note that Arabic support is not included in this release. See the full announcement for details.
UpdateThink: Replace Think Provider Mid-Conversation
You can now dynamically replace the entire Think provider configuration during a live Voice Agent conversation using the new UpdateThink client message. This allows you to switch to a different LLM provider, change the model, set a completely new prompt, and reconfigure functions , all in a single message.