Changelog

​

Model and API Updates

• DeepSeek V4 Flash 0731 is now a separate model from the original DeepSeek V4 Flash, with updated agent benchmarks, a 1M context window, 384K maximum output, reasoning controls, tool use, structured output, server-side web search, and native Responses API support.
• Phaseo now routes DeepSeek’s current deepseek-v4-flash slug to V4 Flash 0731 through the native /responses endpoint. Existing third-party deployments remain attached to the original V4 Flash model, and V4 Pro remains on Chat Completions until DeepSeek enables Responses support for it.
• Official DeepSeek pricing remains $0.0028 per million cached input tokens,$0.14 per million uncached input tokens, and $0.28 per million output tokens. DeepSeek’s announced peak pricing remains pending until an effective date is published.
• Retired direct-provider deepseek-chat and deepseek-reasoner routes and their historical pricing were end-dated at 24 July 2026, 15:59 UTC. Other providers serving the corresponding models are unaffected.

​

Model Releases

• Google: Lyria 3.5
• Google: Gemini Robotics ER 2 Preview
• Google: Gemini Robotics ER 2 Streaming Preview
• xAI: Grok Voice Think Fast 2.0

​

Pricing and Provider Coverage

• Updated GPT-5.6 pricing and added Fast mode, then kept Priority as Phaseo’s canonical UI and billing name while accepting fast as an API alias and preserving priority compatibility. Superseded rules were end-dated, and current Standard, Batch, Flex, cache-write, long-context, and Priority rates were added across eligible OpenAI models.
• Expanded Kimi K3 gateway availability across Nebius Token Factory, Baseten, Fireworks, Wafer, and CrofAI, added Standard, Priority, and Flex routing, and recorded DigitalOcean’s external availability.
• Expanded Morph from specialised code-editing models to a broader inference fleet, with verified routes and pricing for Kimi K3, GLM-5.2, MiniMax M3, Qwen, DeepSeek, and Gemma models.
• Fixed Poolside free-model requests so Phaseo’s routing-only :free suffix is not sent upstream.

​

Features and Platform

• Prepared Phaseo’s read-only MCP for OpenAI plugin submission with ten reviewed model, cost, usage, and request-health tools, privacy-minimised responses, seven resource-bound OAuth scopes, domain verification, and production deployment. Follow-up fixes made dynamic registration and authorization negotiation compatible with Codex while retaining the read-only security boundary.
• Shipped production Agent SDK runtimes for TypeScript, Python, Go, C#, Java, PHP, and Ruby, followed by the Phaseo Rust client and Agent SDK.
• Completed the V2 catalogue cutover, making repository JSON the sole authoring source for 1,238 models, 2,930 routes, 1,978 pricing offers, and 8,249 benchmark results. Subsequent fixes completed the public models-page cutover, restored inactive and coming-soon models, and coordinated immediate Worker and website cache purges so imported changes appear promptly.
• Rebuilt pricing transparency and the comparison calculator around normalized V2 pricing, context-dependent rates, PAYG billing, and clearer BYOK terms.
• Unified Chat and Fusion into one dashboard workspace, with shared navigation, a Fusion beta room, AI-generated-content notices, and gated Video and Realtime rooms.
• Corrected model author names in chat selectors so creators remain distinct from inference providers.

​

Model Releases

• Anthropic: Claude Opus 5

• Model pages are now easier to discover in search.

​

Features

• Improved search discovery across Phaseo and its documentation.

​

Model Releases

• Poolside: Laguna S 2.1
• Qwen: Qwen3.8 Max Preview

​

Features

• Authenticated MCP is now available.
• Benchmark rankings now account for ties more consistently.

​

Features

• Passkeys are now available to all users for passwordless sign-in and account management with device biometrics, PINs, or security keys.
• Chat model selection is faster and works correctly when starting a new chat.

​

Model Releases

• Moonshot AI: Kimi K3

• Thinking Machines: Inkling
• Thinking Machines: Inkling 64K
• Thinking Machines: Inkling Small

​

Features

• Dropdown menus and tab selectors now use Base UI render composition consistently across chat, settings, usage, rankings, and data screens (PR #938).
• The OpenAI GPT-5.6 migration guide was added for Sol, Terra, and Luna readiness planning.
• Model links now store human-readable titles alongside link kinds and preserve multiple links of the same kind.
• Amazon Bedrock provider coverage was staged for SpaceXAI Grok 4.3 with Bedrock Mantle model id xai.grok-4.3, standard pricing, and current us-west-2 in-region availability. The provider-model capability is currently disabled pending setup. AWS currently lists Grok 4.3 as the only SpaceXAI model on Bedrock, and does not list Geo or Global inference for it.
• Amazon Bedrock OpenAI frontier model coverage was checked; AWS still documents GPT-5.5 and GPT-5.4 as regional/Geo in-region offerings, with Global cross-region pricing marked as coming soon.

​

Model Releases

• OpenAI: GPT 5.6 Sol
• OpenAI: GPT 5.6 Terra
• OpenAI: GPT 5.6 Luna
• Muse Spark 1.1 was added with Meta Model API preview metadata, 1M context, benchmark coverage, and titled announcement/API links.

​

Model Releases

• OpenAI: GPT Live 1
• OpenAI: GPT Live 1 Mini
• SpaceXAI: Grok 4.5
• KwaiPilot: Kat Coder Air V2.5
• KwaiPilot: Kat Coder Pro V2.5

​

Features

• Chat now surfaces clearer timing and tool metadata, audio attachments, model-picker focus handling, tag management, and account credit display (PR #922).
• Header search now lazy-loads a compact cached index only when opened, reducing normal dashboard payloads (PR #920).
• Chat streaming, tool-call continuation, and model catalogue cache refresh paths were hardened for more reliable server-tool turns and model pages (PR #919, PR #918).
• API key reveal flows, internal navigation, and new-model Discord notifications were tightened for cleaner settings, admin, and release workflows (PR #812, PR #925, PR #927).
• SiliconFlow provider coverage was added for Tencent Hy3, including the free route and current pricing.
• xAI catalogue and provider labels were renamed to SpaceXAI across model pages, provider records, aliases, logos, and generated SDK/OpenAPI surfaces.
• Aion 1.0 and Aion 1.0 Mini were marked deprecated and retired on July 4, 2026 after Aion Labs removed them from the live model endpoint.

​

Model Releases

• Aion Labs: Aion 3.0
• Aion Labs: Aion 3.0 Mini
• Meta: Muse Image
• Meta: Muse Video
• Sakana: Fugu
• Sakana: Fugu Ultra
• Tencent: Hy3
• Microsoft MAI and Phi catalog entries

​

Features

• AI Stats is now Phaseo across the product, documentation, SDK examples, and public site. Read the migration announcement in AI Stats is becoming Phaseo.
• New developer-facing examples use Phaseo naming and PHASEO_* configuration while existing deployments can keep their current environment-variable names.
• The blog and announcement surfaces were refreshed for the rebrand, including the new migration announcement layout and launch imagery.
• Local, preview, and production builds now use distinct favicons so active environments are easier to tell apart while testing.

​

Model Releases

• OpenAI: GPT Realtime 2.1
• OpenAI: GPT Realtime 2.1 Mini
• Tencent: Hy3

​

Provider Coverage

• Amazon Bedrock Mantle was split into its own provider catalogue with model coverage and pricing for Anthropic, Google, MiniMax, MoonshotAI, NVIDIA, OpenAI, Qwen, SpaceXAI, and Z.AI models.
• AtlasCloud and Novita provider coverage was added for Tencent Hy3, including free-route pricing where available.
• Groq Qwen 3.6 gateway routing was disabled until provider pricing is available.

​

Pricing

• DeepSeek V4 Flash and DeepSeek V4 Pro pricing now supports time-windowed provider rates.

​

Features

• Server-tool inputs, monitor history links, workspace credit cache invalidation, and pricing edge cases were hardened across gateway and web surfaces (PR #900).
• Chat gateway target resolution now fails closed in production when the configured gateway URL is missing, while preserving local-development overrides (PR #899).
• Anthropic and Bedrock request shaping now uses adaptive thinking controls for Claude Sonnet 5 and newer Opus 4.x models (PR #901).
• Server-tool handling was hardened for datetime, web fetch, web search, image generation, and fusion workflows.
• Monitor links now apply stricter URL safety checks.
• GMICloud MiniMax M3 cached-read pricing and Google Vertex Gemini 3.1 Flash-Lite Image pricing validation were tightened.

​

Features

• Chat shortcuts, prompt queue controls, composer tool configuration, restored tags, bulk editing, and richer response timing metadata shipped together for the chat workspace (PR #896).

​

Features

• Individual model pages were overhauled with clearer lifecycle notices, restored routing details, and better handoffs from model pages into gateway workflows (PR #888).
• Retired and replaced model pages now make status, alternatives, and historical context easier to scan without burying the current model link (PR #888).
• Chat tags, tool-call markers, API target controls, and mobile viewport handling were restored or tightened across the chat experience (PR #894, PR #895, PR #891).

​

Features

• Core interactive UI primitives moved onto Base UI, improving accessibility and behaviour consistency across filters, menus, dialogs, and model controls (PR #854).
• Chat and settings flows received follow-up polish after the Base UI migration, including steadier model pickers and cleaner menu spacing (PR #853).

​

Model Releases

• Poolside: Laguna XS 2.1

​

Model Releases

• Anthropic: Claude Fable 5

​

Features

• Pricing calculators now support time-windowed pricing and side-by-side model comparisons, making burst, realtime, and route-specific pricing easier to reason about (PR #864).
• The pricing calculator layout was simplified so model, provider, and usage assumptions are easier to adjust before comparing costs (PR #864).

​

Model Releases

• Anthropic: Claude Sonnet 5
• Google: Gemini Omni Flash Preview
• Mistral: Leanstral 1.5
• Mistral: OCR 4

​

Model Releases

• Meituan: LongCat 2.0

​

Model Releases

• Google: Gemini 3.1 Flash Lite image (Nano Banana 2 Lite)
• ByteDance: Seed 2.1 Turbo
• z.AI: GLM 5.2 Fast

​

Model Releases

• xAI: Grok Imagine Video 1.5

​

Model Releases

• z.AI: GLM 5.2

​

Model Releases

• ByteDance: Seedance 2.0 Mini (2026-06-15)

​

Model Releases

• CrofAI: Greg 2 Super
• CrofAI: Greg 2 Ultra

​

Model Releases

• Moonshot: Kimi K2.7 Code

​

Model Releases

• z.AI: GLM 5.2

​

Model Releases

• Google: DiffusionGemma 26B A4B IT

​

Model Releases

• Anthropic: Claude Fable 5
• Anthropic: Claude Mythos 5
• Google: Gemini 3.5 Live Translate Preview

​

Model Releases

• Nex AGI: Nex N2 Mini
• Nex AGI: Nex N2 Pro

​

Model Releases

• Google: Gemma 4 12B

​

Model Releases

• MiniMax: MiniMax M3
• Nvidia: Nemotron 3 Ultra
• Qwen: Qwen 3.7 Plus

​

Model Releases

• Nvidia: Cosmos3 Super Reasoner

​

Model Releases

• xAI: Grok Imagine Video 1.5 Preview

​

Model Releases

• StepFun: Step 3.7 Flash

​

Features

• Pricing selectors now present Qwen 3.7 Max variants more clearly, reducing ambiguity between preview, dated, and current model routes (PR #418).
• Anthropic-on-AWS provider branding was refreshed so Bedrock and Claude Platform routes are easier to distinguish in provider lists (PR #415).

​

Model Releases

• Anthropic: Claude Opus 4.8
• CrofAI: Greg RP
• Google: Gemini 3 Pro Image (Nano Banana Pro)
• Google: Gemini 3.1 Flash Image (Nano Banana 2)

​

Model Releases

• Qwen: Qwen 3.7 Plus (2026-05-26)

​

Model Releases

• Qwen: Qwen 3.7 Max (2026-05-17)
• Qwen: Qwen 3.7 Max Preview

​

Model Releases

• Qwen: Qwen 3.7 Max

​

Model Releases

• Cohere: Command A+

​

SDK Releases

• The TypeScript Agent SDK launch added a dedicated package for building agentic applications on top of Phaseo Gateway (PR #495). See @phaseo/agent-sdk.

​

Model Releases

• Google: Gemini 3.5 Flash
• Qwen: Qwen 3.5 LiveTranslate Flash Realtime (2026-05-19)

​

Model Releases

• Cursor: Composer 2.5

​

Features

• Provider activation states and region filters were tightened so unavailable routes are easier to identify before a request is made (PR #495).
• Free-router behaviour was made more predictable across pricing, provider selection, and gateway routing surfaces (PR #495).

​

SDK Releases

• Agent SDK documentation and examples shipped with the first public workflow guidance for durable loops, parallel tools, and agent orchestration (PR #495).

​

Model Releases

• xAI: Grok TTS

​

Model Releases

• xAI: Grok Build 0.1

​

Features

• Provider availability and pricing summaries were expanded so model pages show clearer route, tier, and cost differences (PR #474).
• Realtime minute pricing became visible in the product, making audio and live-session models easier to compare against token-priced models (PR #477).

​

Model Releases

• Google: Gemini 3.1 Flash-Lite
• OpenAI: GPT Realtime 2
• OpenAI: GPT Realtime Translate
• OpenAI: GPT Realtime Whisper

​

Features

• Video generation and async job lifecycle coverage expanded, including clearer status handling for long-running provider work (PR #468).
• Gateway surfaces now expose more of the reservation, completion, and failure states needed to debug async media requests (PR #468).

​

Model Releases

• xAI: Grok Imagine Image Quality

​

Model Releases

• OpenAI: chat-latest

​

SDK Releases

• TypeScript SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.
• Python SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.
• Go SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.
• C# SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.
• Java SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.
• PHP SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.
• Ruby SDK 2.0.4: generated OpenAPI and model-surface updates for the latest gateway schema.

​

Model Releases

• xAI: Grok 4.3

​

SDK Releases

• SDK 2.0.2 shipped for TypeScript, Python, Go, C#, Java, PHP, and Ruby.
• This release separated runtime request model IDs from generated callable-helper constants, so newly released models can be used before the next SDK publish.
• Generated helpers now track the current callable-on-gateway snapshot, reducing noisy SDK churn from catalog-only model updates.

​

Model Releases

• IBM: Granite 4.1 30B
• IBM: Granite 4.1 3B
• IBM: Granite 4.1 8B
• Mistral: Mistral Medium 3.5

​

Model Releases

• ByteDance: Seed 2.0 Lite (2026-04-28)
• ByteDance: Seed 2.0 Mini (2026-04-28)
• Nvidia: Nemotron 3 Nano Omni 30B A3B Reasoning
• Poolside: Laguna XS.2

​

Features

• Low-balance alerts and billing safeguards were expanded so teams get clearer warning before usage runs into account limits (PR #371).
• Pricing edge cases now fail more predictably when provider billing rules are incomplete or route metadata changes unexpectedly (PR #374).

​

Model Releases

• DeepSeek: DeepSeek V4 Pro Lightning

​

Model Releases

• DeepSeek: DeepSeek V4 Flash
• DeepSeek: DeepSeek V4 Pro

​

Model Releases

• OpenAI: GPT 5.5
• OpenAI: GPT 5.5 Pro
• Tencent Hunyuan: Hy3 Preview

​

Features

• SDK 2.0.0 shipped with regenerated clients and broader parity against the current gateway contract.

​

Model Releases

• Google: Gemini Embedding 2
• Qwen: Qwen 3.6 27B
• Xiaomi: MiMo V2.5
• Xiaomi: MiMo V2.5 Pro
• Xiaomi: MiMo V2.5 TTS

​

Features

• The announcements hub, workspace management surfaces, and related membership flows shipped.

​

Model Releases

• Google: Gemini Deep Research Max Preview (04-2026)
• Google: Gemini Deep Research Preview (04-2026)
• OpenAI: GPT Image 2

​

Model Releases

• Moonshot: Kimi K2.6
• Qwen: Qwen 3.5 Plus (2026-04-20)

​

Features

• SDK 1.2.0 synced model availability, generated types, and docs with the latest catalog changes.

​

Model Releases

• xAI: Grok TTS

​

Model Releases

• Anthropic: Claude Opus 4.7

​

Model Releases

• Google: Gemini 3.1 Flash TTS Preview
• Qwen: Qwen 3.6 35B A3B

​

Model Releases

• Google: Gemini Robotics ER 1.6 Preview

​

Model Releases

• Moonshot: Kimi K2.6 Code Preview

​

Model Releases

• MiniMax: Music 2.6

​

Model Releases

• Meta: Muse Spark
• Meta: Muse Spark Contemplating

​

Model Releases

• z.AI: GLM 5.1

​

Features

• Mobile model pages, pricing layouts, and free-route visibility were improved, and the Pay As You Go top-up fee dropped to 5%.

​

Model Releases

• Qwen: Wan 2.7 T2V

​

Model Releases

• Google: Gemma 4 26B A4B
• Google: Gemma 4 31B

​

Model Releases

• Arcee AI: Trinity Large Thinking
• Qwen: Qwen 3.6 Plus
• z.AI: GLM 5V Turbo

​

Model Releases

• Google: Veo 3.1 Lite Preview

​

Model Releases

• Mistral: Voxtral TTS

​

Features

• New language SDKs shipped, TypeScript and Python SDKs were overhauled, and chat rooms went multimodal.
• Foundry launched, LLM Council became the first Foundry project, and SDK 1.1.0 aligned model availability and lifecycle warnings with the API.

​

Model Releases

• Xiaomi: MiMo V2 Omni
• Xiaomi: MiMo V2 Pro
• Xiaomi: MiMo V2 TTS

​

Model Releases

• MiniMax: MiniMax M2.7
• Xiaomi: MiMo V2 Omni
• Xiaomi: MiMo V2 Pro
• Xiaomi: MiMo V2 TTS

​

Model Releases

• Mistral: Mistral Moderation 2
• OpenAI: GPT 5.4 Mini
• OpenAI: GPT 5.4 Nano

​

Model Releases

• Mistral: Leanstral
• Mistral: Mistral Small 4

​

Model Releases

• z.AI: GLM 5 Turbo

​

Features

• The models display page was overhauled for clearer availability, metadata hierarchy, and support context.

​

Model Releases

• Nvidia: Nemotron 3 Super

​

Model Releases

• Nvidia: Nemotron 3 Super

​

Features

• A broader brand refresh shipped across the website and docs.
• Alibaba Cloud provider coverage landed across Phaseo, gateway routes, and documentation.

​

Model Releases

• Aion Labs: Aion 2.5
• Google: Gemini Embedding 2 Preview

​

Features

• GPT 5.4 and GPT 5.4 Pro landed across discovery, gateway, and docs.

​

Model Releases

• OpenAI: GPT 5.4
• OpenAI: GPT 5.4 Pro

​

Features

• Gemini 3.1 Flash Lite Preview landed across product surfaces, gateway routing, and docs.

​

Model Releases

• Google: Gemini 3.1 Flash Lite Preview
• OpenAI: GPT 5.3 Chat

​

Features

• Responses API assistant phase support landed across request handling, response payloads, and OpenAPI docs.

​

Model Releases

• Qwen: Qwen 3.5 0.8B
• Qwen: Qwen 3.5 2B
• Qwen: Qwen 3.5 4B
• Qwen: Qwen 3.5 9B

​

Features

• Gemini 3.1 Flash Image Preview support landed across discovery, gateway compatibility, and docs.

​

Model Releases

• Google: Gemini 3.1 Flash Image Preview (Nano Banana 2)

​

Model Releases

• Inception: Mercury 2
• Inception: Mercury Edit 2
• Liquid AI: LFM 2 24B A2B
• Qwen: Qwen 3.5 122B A10B
• Qwen: Qwen 3.5 27B
• Qwen: Qwen 3.5 35B A3B

​

Model Releases

• OpenAI: GPT Audio 1.5
• OpenAI: GPT Realtime 1.5
• Qwen: Qwen 3.5 Flash

​

Features

• Gemini 3.1 Pro Preview coverage landed across discovery, pricing, gateway support, and docs.

​

Model Releases

• Google: Gemini 3.1 Pro Preview
• Google: Gemini 3.1 Pro Preview Customtools

​

Features

• Claude Sonnet 4.6 coverage landed across discovery, gateway compatibility, and docs.

​

Model Releases

• Google: Lyria 3
• Prime Intellect: Intellect 3.1

​

Model Releases

• Anthropic: Claude Sonnet 4.6
• Cohere: Tiny Aya Earth
• Cohere: Tiny Aya Fire
• Cohere: Tiny Aya Global
• Cohere: Tiny Aya Water
• xAI: Grok 4.20
• xAI: Grok 4.20 Multi Agent Beta

​

Model Releases

• Qwen: Qwen 3.5 397B A17B
• Qwen: Qwen 3.5 Plus
• Qwen: Qwen 3.5 Plus (2026-02-15)

​

Model Releases

• ByteDance: Seed 2.0 Code Preview (2026-02-15)

​

Model Releases

• ByteDance: Seed 2.0 Lite
• ByteDance: Seed 2.0 Mini
• ByteDance: Seed 2.0 Pro

​

Model Releases

• ByteDance: Seedance 2.0
• ByteDance: Seedance 2.0 Fast
• Inclusion AI: Ring 1T 2.5
• MiniMax: MiniMax M2.5
• OpenAI: GPT 5.3 Codex Spark

​

Model Releases

• z.AI: GLM 5

​

Model Releases

• Cursor: Composer 1.5

​

Model Releases

• Anthropic: Claude Opus 4.6
• OpenAI: GPT 5.3 Codex

​

Model Releases

• Mistral: Voxtral Mini Transcribe 2

​

Features

• The gateway was overhauled again, including Anthropic-compatible /messages support.
• Database architecture, website UX, playground tooling, and SDK direction were all refreshed for broader expansion.

​

Model Releases

• z.AI: GLM 4.5 Air X
• z.AI: GLM 4.5 X
• xAI: Grok Imagine Image
• xAI: Grok Imagine Video
• Moonshot: Kimi K2.5
• MiniMax: MiniMax M2 Her
• Qwen: Qwen 3 Max Thinking

​

Model Releases

• xAI: Grok Imagine Image
• xAI: Grok Imagine Image Pro
• xAI: Grok Imagine Video

​

Model Releases

• Arcee AI: Trinity Large
• CrofAI: Greg 1
• CrofAI: Greg 1 Mini
• CrofAI: Greg 1 Super
• Moonshot: Kimi K2.5

​

Model Releases

• Qwen: Qwen 3 Max Thinking
• Upstage: Solar Pro 3 (2026-01-26)

​

Model Releases

• MiniMax: MiniMax M2 Her

​

Model Releases

• Baidu: Ernie 5.0

​

Model Releases

• Liquid AI: LFM 2.5 1.2B Thinking

​

Model Releases

• z.AI: GLM 4.7 Flash

​

Model Releases

• MiniMax: Music 2.5

​

Model Releases

• Black Forest Labs: Flux 2 Klein 4B
• Black Forest Labs: Flux 2 Klein 9B
• Google: TranslateGemma 12B
• Google: TranslateGemma 27B
• Google: TranslateGemma 4B
• Voyage: Voyage 4
• Voyage: Voyage 4 Large
• Voyage: Voyage 4 Lite
• Voyage: Voyage Multimodal 3.5

​

Model Releases

• z.AI: GLM Image

​

Model Releases

• Google: MedGemma 1.5 4B

​

Model Releases

• ElevenLabs: Scribe V2

​

Model Releases

• ai21: Jamba 2 3B
• ai21: Jamba Mini 2

​

Model Releases

• Liquid AI: LFM 2.5 1.2B
• Liquid AI: LFM 2.5 1.2B JP
• Nous: NousCoder 14B

​

Model Releases

• z.AI: GLM 4.7
• MiniMax: Music 2.0
• Relace: Relace Search
• ByteDance: Seed 1.6 (2025-10-15)
• ByteDance: Seed 1.6 Flash (2025-08-28)
• ByteDance: Seed 1.8
• ByteDance: Seedream 4.5
• MiniMax: Speech 2.6
• Arcee AI: Trinity Large

​

Model Releases

• LG: K EXAONE

​

Model Releases

• NAVER: HyperClova X Seed Omni 8B
• NAVER: HyperClova X Seed Think 32B

​

Model Releases

• ByteDance: Seed 1.8 (2025-12-28)

​

Model Releases

• MiniMax: MiniMax M2.1

​

Model Releases

• z.AI: GLM 4.7

​

Model Releases

• Aion Labs: Aion 2.0

​

Model Releases

• z.AI: GLM 4.7
• OpenAI: GPT 5.2 Codex
• Mistral: OCR 3

​

Model Releases

• ByteDance: Seed 1.8
• Mistral: OCR 3
• OpenAI: GPT 5.2 Codex

​

Model Releases

• Google: Gemini 3 Flash Preview

​

Model Releases

• AllenAI: Molmo 2 4B
• AllenAI: Molmo 2 8B
• Black Forest Labs: Flux 2 Max
• Mistral: Mistral Small Creative
• OpenAI: ChatGPT Image Latest
• OpenAI: GPT Image 1.5
• Xiaomi: MiMo V2 Flash

​

Features

• Early alpha SDK releases landed for Python and TypeScript or JavaScript.

​

Model Releases

• AllenAI: Bolmo 1B
• AllenAI: Bolmo 7B
• Nvidia: Nemotron Nano 3 30B A3B
• OpenAI: GPT 4o Mini Transcribe (2025-12-15)
• OpenAI: GPT 4o Mini TTS (2025-12-15)
• OpenAI: GPT Audio Mini (2025-12-15)
• OpenAI: GPT Realtime Mini (2025-12-15)
• Upstage: Solar Pro 2 (2025-12-15)

​

Features

• OpenAI-compatible /responses support, aligned SDKs, and gateway quickstart or pricing page updates shipped.
• Docs expanded ahead of the SDK launch, and nightly CI started automatically refreshing model statuses.

​

Model Releases

• AllenAI: Olmo 3.1 32B Instruct
• AllenAI: Olmo 3.1 32B Think
• Google: Gemini 2.5 Flash Native Audio Preview (2025-12-12)

​

Model Releases

• Cohere: Rerank V4.0 Fast
• Cohere: Rerank V4.0 Pro
• OpenAI: GPT 5.2
• OpenAI: GPT 5.2 Chat
• OpenAI: GPT 5.2 Pro

​

Model Releases

• Google: Gemini 2.5 Flash Preview TTS (2025-12-10)
• Google: Gemini 2.5 Pro Preview TTS (2025-12-10)

​

Model Releases

• Mistral: Devstral 2.0
• Mistral: Devstral Small 2.0
• Nous: Nomos 1

​

Model Releases

• OpenAI: Sora 2 (2025-12-08)
• z.AI: GLM 4.6V
• z.AI: GLM 4.6V Flash

​

Model Releases

• Essential AI: Rnj-1

​

Features

• Dark mode shipped.

​

Model Releases

• ByteDance: Seedream 4.5
• Nous: Hermes 4.3 36B

​

Model Releases

• Amazon: Nova 2 Lite
• Amazon: Nova 2 Omni
• Amazon: Nova 2 Pro
• Amazon: Nova 2 Sonic
• Amazon: Nova Multimodal Embeddings
• Mistral: Ministral 3.0 14B
• Mistral: Ministral 3.0 3B
• Mistral: Ministral 3.0 8B
• Mistral: Mistral Large 3.0

​

Features

• Phaseo relaunched with a refreshed brand, a broader gateway, and much wider data coverage.
• Model availability, benchmark pages, provider pages, and the latest-updates surfaces were overhauled.
• The unified gateway entered alpha, and the first Python and TypeScript or JavaScript SDKs launched alongside it.

​

Model Releases

• Arcee AI: Trinity Mini
• Arcee AI: Trinity Nano Preview
• DeepSeek: DeepSeek V3.2
• DeepSeek: DeepSeek V3.2 Speciale
• DeepSeek: DeepSeek V3.2 Thinking

​

Model Releases

• Prime Intellect: Intellect 3

​

Model Releases

• Black Forest Labs: Flux 2 Dev
• Black Forest Labs: Flux 2 Flex
• Black Forest Labs: Flux 2 Pro

​

Model Releases

• Anthropic: Claude Opus 4.5

​

Model Releases

• AllenAI: Olmo 3 32B Think
• AllenAI: Olmo 3 7B Instruct
• AllenAI: Olmo 3 7B Think
• Google: Gemini 3 Pro Image Preview (Nano Banana Pro)

​

Model Releases

• OpenAI: GPT 5.1 Codex Max

​

Model Releases

• Google: Gemini 3 Pro Preview

​

Model Releases

• xAI: Grok 4.1 Non Thinking
• xAI: Grok 4.1 Thinking

​

Model Releases

• OpenAI: GPT 5.1 Chat
• OpenAI: GPT 5.1 Codex
• OpenAI: GPT 5.1 Codex Mini

​

Model Releases

• OpenAI: GPT 5.1

​

Model Releases

• ElevenLabs: Scribe V2 Realtime

​

Model Releases

• OpenAI: GPT 5 Codex Mini

​

Model Releases

• Moonshot: Kimi K2 Thinking

​

Model Releases

• Moonshot: Kimi Linear 48B

​

Model Releases

• Cursor: Composer 1
• MiniMax: Music 2.0
• MiniMax: Speech 2.6
• OpenAI: GPT OSS Safeguard 120b
• OpenAI: GPT OSS Safeguard 20b

​

Model Releases

• MiniMax: Hailuo 2.3
• MiniMax: Hailuo 2.3 Fast

​

Model Releases

• MiniMax: MiniMax M2
• Suno: Suno V4.5 All

​

Model Releases

• DeepSeek: DeepSeek OCR

​

Model Releases

• Anthropic: Claude Haiku 4.5
• ByteDance: Seed 1.6 (2025-10-15)
• Google: Veo 3.1 Fast Preview
• Google: Veo 3.1 Preview
• OpenAI: GPT 4o Transcribe Diarize

​

Model Releases

• OpenAI: GPT 5 Search API

​

Model Releases

• ai21: Jamba Reasoning 3B

​

Model Releases

• Google: Gemini 2.5 Computer Use Preview
• Liquid AI: LFM 2 8B A1B

​

Model Releases

• OpenAI: GPT Audio Mini (2025-10-06)
• OpenAI: GPT Image 1 Mini
• OpenAI: GPT Realtime Mini (2025-10-06)

​

Model Releases

• OpenAI: Sora 2 Pro

​

Model Releases

• Google: Gemini 2.5 Flash Image (Nano Banana)
• IBM: Granite 4.0 Micro
• IBM: Granite 4.0 Small
• IBM: Granite 4.0 Tiny

​

Model Releases

• OpenAI: Sora 2 (2025-09-30)
• z.AI: GLM 4.6

​

Model Releases

• Anthropic: Claude Sonnet 4.5
• DeepSeek: DeepSeek V3.2 Exp

​

Model Releases

• Google: Gemini 2.5 Flash Lite Preview (2025-09-25)
• Google: Gemini 2.5 Flash Preview (2025-09-25)
• Google: Gemini Robotics ER 1.5 Preview

​

Model Releases

• Liquid AI: LFM 2 2.6B
• Suno: Suno V5

​

Model Releases

• DeepSeek: DeepSeek V3.1 Terminus
• Qwen: Qwen3 LiveTranslate Flash Realtime

​

Model Releases

• xAI: Grok 4 Fast Non Reasoning
• xAI: Grok 4 Fast Reasoning

​

Model Releases

• Inclusion AI: Ring Flash 2.0

​

Model Releases

• Inclusion AI: Ling Flash 2.0
• Mistral: Magistral Medium 1.2
• Mistral: Magistral Small 1.2

​

Model Releases

• OpenAI: GPT 5 Codex

​

Model Releases

• Google: Veo 3
• Google: Veo 3 Fast
• Upstage: Solar Pro 2 (2025-09-09)

​

Model Releases

• Moonshot: Kimi K2 (2025-09-05)

​

Model Releases

• ByteDance: Seed 1.6 Flash (2025-08-28)
• Cohere: Command A Translate
• OpenAI: GPT Audio
• OpenAI: GPT Realtime
• xAI: Grok Code Fast 1

​

Model Releases

• Google: Gemini 2.5 Flash Image Preview (Nano Banana)

​

Model Releases

• Cohere: Command A Reasoning
• DeepSeek: DeepSeek V3.1

​

Model Releases

• Google: Imagen 4.0 Fast Generate 001
• Google: Imagen 4.0 Generate 001
• Google: Imagen 4.0 Ultra Generate 001

​

Model Releases

• Mistral: Mistral Medium 3.1

​

Model Releases

• z.AI: GLM 4.5V

​

Model Releases

• OpenAI: GPT 5
• OpenAI: GPT 5 Chat
• OpenAI: GPT 5 Mini
• OpenAI: GPT 5 Nano
• OpenAI: GPT 5 Pro

​

Model Releases

• MiniMax: Speech 2.5 HD Preview
• MiniMax: Speech 2.5 Turbo Preview

​

Model Releases

• Anthropic: Claude Opus 4.1
• OpenAI: GPT OSS 120b
• OpenAI: GPT OSS 20b

​

Model Releases

• Cohere: Command A Vision

​

Model Releases

• Mistral: Codestral (2025-07-30)

​

Model Releases

• z.AI: GLM 4.5
• z.AI: GLM 4.5 Air

​

Model Releases

• Nous: Hermes 4 14B
• Nous: Hermes 4 405B
• Nous: Hermes 4 70B

​

Model Releases

• Mistral: Magistral Medium 1.1
• Mistral: Magistral Small 1.1

​

Model Releases

• Google: Gemini 2.5 Flash-Lite
• NAVER: HyperClova X Seed Think 14B

​

Model Releases

• Google: Veo 3.0 Fast Generate Preview
• Google: Veo 3.0 Generate Preview
• Suno: Suno V4.5+

​

Model Releases

• LG: EXAONE 4.0 1.2B
• LG: EXAONE 4.0 32B
• Mistral: Voxtral Mini
• Mistral: Voxtral Mini Transcribe
• Mistral: Voxtral Small

​

Model Releases

• Moonshot: Kimi K2 (2025-07-11)

​

Model Releases

• Liquid AI: LFM 2 1.2B
• Liquid AI: LFM 2 350M
• Liquid AI: LFM 2 700M
• Mistral: Devstral Medium 1.0
• Mistral: Devstral Small 1.1
• Upstage: Solar Pro 2 (2025-07-10)
• xAI: Grok 4
• xAI: Grok 4 Heavy

​

Model Releases

• ai21: Jamba Large 1.7
• ai21: Jamba Mini 1.7

​

Model Releases

• z.AI: GLM 4.1V 9B
• z.AI: GLM 4.1V Thinking 9B

​

Model Releases

• Tencent Hunyuan: Hunyuan A13B Instruct

​

Model Releases

• OpenAI: o3 Deep Research
• OpenAI: o4 mini Deep Research

​

Model Releases

• ByteDance: Seed 1.6 (2025-06-15)
• ByteDance: Seed 1.6 Flash (2025-06-15)
• Google: Gemma 3n E2B
• Google: Gemma 3n E4B

​

Model Releases

• Moonshot: Kimi VL A3B Thinking (2025-06-21)

​

Model Releases

• MiniMax: Music 1.5
• Mistral: Mistral Small 3.2

​

Model Releases

• MiniMax: Hailuo 02

​

Model Releases

• Google: Gemini 2.5 Flash
• Google: Gemini 2.5 Flash Lite Preview (2025-06-17)
• Google: Gemini 2.5 Pro

​

Model Releases

• MiniMax: Minimax M1 40K
• MiniMax: MiniMax M1 80K

​

Model Releases

• Google: Imagen 4.0 Fast Generate Preview (2025-06-11)
• Google: Imagen 4.0 Generate Preview (2025-06-11)
• Google: Imagen 4.0 Ultra Generate Preview (2025-06-11)

​

Model Releases

• Mistral: Magistral Medium 1.0
• Mistral: Magistral Small 1.0
• Mistral: Magistral Small 2506
• OpenAI: o3 Pro

​

Model Releases

• Google: Gemini 2.5 Pro Preview (2025-06-05)

​

Model Releases

• OpenAI: GPT 4o Audio (2025-06-03)
• OpenAI: GPT 4o Realtime Preview (2025-06-03)

​

Model Releases

• DeepSeek: DeepSeek R1 (2025-05-28)
• Mistral: Codestral Embed

​

Model Releases

• Mistral: Mistral OCR 2

​

Model Releases

• Anthropic: Claude Opus 4
• Anthropic: Claude Sonnet 4
• Mistral: Devstral Small 1.0

​

Model Releases

• Google: Gemini 2.5 Flash Preview (2025-05-20)
• Google: Gemini 2.5 Flash Preview TTS (2025-05-20)
• Google: Gemini 2.5 Pro Preview TTS (2025-05-20)
• Google: Gemini Embedding 001
• Google: Imagen 4.0 Preview
• Google: Imagen 4.0 Ultra Preview
• Upstage: Solar Pro 2 Preview

​

Model Releases

• OpenAI: Codex Mini

​

Model Releases

• Google: Gemini 2.0 Flash Preview Image Generation
• Mistral: Mistral Medium 3.0

​

Model Releases

• Google: Gemini 2.5 Pro Preview (2025-05-06)

​

Model Releases

• IBM: Granite 4.0 Tiny Preview

​

Model Releases

• Suno: Suno V4.5

​

Model Releases

• Amazon: Nova Premier
• Microsoft: Phi 4 Mini Reasoning
• Microsoft: Phi 4 Reasoning
• Microsoft: Phi 4 Reasoning Plus

​

Model Releases

• OpenAI: GPT Image 1

​

Model Releases

• xAI: Grok 3
• xAI: Grok 3 Mini

​

Model Releases

• Google: Gemini 2.5 Flash Preview (2025-04-17)
• Google: LearnLM 2.0 Flash Experimental

​

Model Releases

• IBM: Granite 3.3 2B Instruct
• IBM: Granite 3.3 8B Instruct
• OpenAI: o3
• OpenAI: o4 Mini

​

Model Releases

• Cohere: Embed V4
• z.AI: GLM 4 32B

​

Model Releases

• OpenAI: GPT 4.1
• OpenAI: GPT 4.1 Mini
• OpenAI: GPT 4.1 Nano
• z.AI: GLM 4 9B (2025-04-14)

​

Model Releases

• Google: Gemini 2.0 Flash Live 001
• Google: Gemini Live 2.5 Flash Preview
• Google: Veo 2
• Moonshot: Kimi VL A3B
• Moonshot: Kimi VL A3B Thinking (2025-04-09)

​

Model Releases

• Amazon: Nova Sonic

​

Model Releases

• Nvidia: Llama 3.1 Nemotron Ultra 253B v1

​

Model Releases

• Meta: Llama 4 Maverick
• Meta: Llama 4 Scout

​

Model Releases

• MiniMax: Speech 02 HD
• MiniMax: Speech 02 Turbo

​

Model Releases

• Google: Gemini 2.5 Pro Experimental (2025-03-25)

​

Model Releases

• DeepSeek: DeepSeek V3 (2025-03-24)
• Qwen: Qwen 2.5 VL 32B Instruct

​

Model Releases

• OpenAI: GPT 4o Mini Transcribe (2025-03-20)
• OpenAI: GPT 4o Mini TTS (2025-03-20)
• OpenAI: GPT 4o Transcribe

​

Model Releases

• OpenAI: o1 pro

​

Model Releases

• LG: EXAONE Deep 2.4B
• LG: EXAONE Deep 32B
• LG: EXAONE Deep 7.8B
• Nvidia: Llama 3.1 Nemotron Nano 8B V1
• Nvidia: Llama 3.3 Nemotron Super 49B v1

​

Model Releases

• Mistral: Mistral Small 3.1

​

Model Releases

• Cohere: Command A

​

Model Releases

• Google: Gemma 3 12B
• Google: Gemma 3 1B
• Google: Gemma 3 27B
• Google: Gemma 3 4B

​

Model Releases

• OpenAI: Computer Use Preview
• OpenAI: GPT 4o Mini Search Preview
• OpenAI: GPT 4o Search Preview

​

Model Releases

• Google: Gemini Embedding Exp 0307

​

Model Releases

• ai21: Jamba Large 1.6
• ai21: Jamba Mini 1.6
• Mistral: Mistral OCR

​

Model Releases

• Cohere: C4AI Aya Vision 32B
• Cohere: C4AI Aya Vision 8B

​

Model Releases

• OpenAI: GPT 4.5

​

Model Releases

• Anthropic: Claude 3.7 Sonnet

​

Model Releases

• xAI: Grok 3 Beta
• xAI: Grok 3 Mini Beta

​

Model Releases

• Mistral: Mistral Saba

​

Model Releases

• MiniMax: Image 01

​

Model Releases

• MiniMax: I2V 01 Director
• MiniMax: T2V 01 Director

​

Model Releases

• Google: Gemini 2.0 Flash
• Google: Gemini 2.0 Flash Lite
• Google: Gemini 2.0 Pro Exp (2025-02-05)

​

Model Releases

• Microsoft: Phi 4 Mini
• Microsoft: Phi 4 multimodal instruct

​

Model Releases

• Mistral: Mistral Small 24b 2501
• Mistral: Mistral Small 3.0
• OpenAI: o3 mini

​

Model Releases

• Aion Labs: Aion 1.0
• Aion Labs: Aion 1.0 Mini
• Google: Imagen 3.0 Generate 002

​

Model Releases

• Qwen: Qwen 2.5 VL 72B Instruct

​

Model Releases

• Google: Gemini 2.0 Flash Thinking Exp (2025-01-21)

​

Model Releases

• DeepSeek: DeepSeek R1 (2025-01-20)
• Moonshot: Kimi K1.5

​

Model Releases

• MiniMax: Minimax Text 01
• MiniMax: Minimax VL 01

​

Model Releases

• Mistral: Codestral (2025-01-13)

​

Model Releases

• DeepSeek: DeepSeek V3
• DeepSeek: DeepSeek V3 (2024-12-26)

​

Model Releases

• Google: Gemini 2.0 Flash Thinking Exp (2024-12-19)

​

Model Releases

• OpenAI: GPT 4o Audio (2024-12-17)
• OpenAI: GPT 4o Mini Audio Preview
• OpenAI: GPT 4o Mini Realtime Preview
• OpenAI: GPT 4o Realtime Preview (2024-12-17)
• OpenAI: o1