As of: 2026-10-07 23:43 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code). Human editor: Adam Bicz.
Canonical page: https://postcutoff.com/models/

# AI models and how to call them

298 models, with model ids per provider, prices with a source, and the date we last checked. 53 publish a training cutoff.

Prices are per 1M tokens in USD unless stated, as published by the provider on the date the model was last checked. Each model page lists every provider, model id, endpoint and docs link.

## Assistants people use

- ChatGPT: GPT-6 Astra (`gpt-6-astra`), knows up to April 2026, 725 events after its cutoff. https://postcutoff.com/m/gpt-6-astra/ Also in ChatGPT: GPT-6.1 Sol, GPT-6 Luna, GPT-6 Sol.
- Claude: Claude Opus 5.5 (`claude-opus-5-5`), knows up to June 2026, 665 events after its cutoff. https://postcutoff.com/m/claude-opus-5-5/ Also in Claude: Claude Sonnet 5.5, Claude Fable 5.1.
- Gemini: Gemini 3.8 Flash (`gemini-3.8-flash`), knows up to March 2026, 747 events after its cutoff. https://postcutoff.com/m/gemini-3-8-flash/
- Grok: Grok 4.7 (`grok-4.7`), knows up to May 2026, 694 events after its cutoff. https://postcutoff.com/m/grok-4-7/

## Registry, newest first

| Model | Maker | Released | Status | Type | Model id | Cutoff | Events after cutoff | Price | Checked |
|---|---|---|---|---|---|---|---|---|---|
| [EmbeddingGemma 2](https://postcutoff.com/m/embeddinggemma-2/) | Google DeepMind | 2026-10-06 | current | embedding | `google/embeddinggemma-2` |  |  | Price not published | 2026-10-07 |
| [Mistral Large 4](https://postcutoff.com/m/mistral-large-4/) | Mistral AI | 2026-10-06 | preview | multimodal | `mistral-large-4-0` |  |  | $0.68 in, $2.09 out per 1M tokens | 2026-10-06 |
| [Nano Banana 2.1 (Gemini Nano Banana 2.1)](https://postcutoff.com/m/gemini-nano-banana-2-1/) | Google DeepMind | 2026-10-06 | current | image-gen | `gemini-nano-banana-2.1` | 2026-03 | 747 | $1.50 in, $7.50 out per 1M tokens | 2026-10-07 |
| [Beam (Beam-501B-A23B)](https://postcutoff.com/m/reflection-beam/) | Reflection AI | 2026-10-05 | preview | reasoning-llm | `Beam-501B-A23B` | 2026-06 | 665 | Price not published | 2026-10-05 |
| [Kolibri-1](https://postcutoff.com/m/kolibri-1/) | Aleph Alpha | 2026-10-03 | current | reasoning-llm |  | 2026-06 | 665 | Price not published | 2026-10-03 |
| [Cactus Whistle (16.9 MB on-device speech-to-text)](https://postcutoff.com/m/cactus-whistle/) | Cactus Compute | 2026-10-02 | current | audio/speech | `Cactus-Compute/whistle` |  |  | Price not published | 2026-10-03 |
| [Clef](https://postcutoff.com/m/cloudflare-clef/) | Cloudflare | 2026-10-01 | current | llm | `@cf/cloudflare/clef` |  |  | $0.24 in per 1M tokens; output price not published | 2026-10-02 |
| [Clef-flash](https://postcutoff.com/m/cloudflare-clef-flash/) | Cloudflare | 2026-10-01 | current | llm | `@cf/cloudflare/clef-flash` |  |  | Price not published | 2026-10-02 |
| [MAI-Transcribe-2-Streaming](https://postcutoff.com/m/mai-transcribe-2-streaming/) | Microsoft | 2026-10-01 | current | audio/speech |  |  |  | $0.54 per hour | 2026-10-02 |
| [MAI-Voice-2.1 / MAI-Voice-2.1-Flash](https://postcutoff.com/m/mai-voice-2-1/) | Microsoft | 2026-10-01 | current | audio/speech |  |  |  | $22 per 1M characters | 2026-10-02 |
| [pplx-decider-v1-27b](https://postcutoff.com/m/pplx-decider-v1-27b/) | Perplexity | 2026-10-01 | current | llm | `pplx-decider-v1-27b` |  |  | $0.04 in per 1M tokens; output free | 2026-10-03 |
| [Strands Decider 2B](https://postcutoff.com/m/strands-decider-2b/) | Amazon Web Services (Strands Labs) | 2026-10-01 | preview | llm |  |  |  | Free | 2026-10-01 |
| [Tavus Griffin (Human Interaction Model)](https://postcutoff.com/m/tavus-griffin/) | Tavus | 2026-10-01 | preview | video-gen |  |  |  | Price not published | 2026-10-02 |
| [Cohere Embed 5 Fast](https://postcutoff.com/m/cohere-embed-v5-fast/) | Cohere | 2026-09-30 | current | embedding | `embed-v5.0-fast` |  |  | $0.08 in per 1M tokens | 2026-10-01 |
| [Cohere Embed 5 Pro](https://postcutoff.com/m/cohere-embed-v5-pro/) | Cohere | 2026-09-30 | current | embedding | `embed-v5.0-pro` |  |  | $0.12 in per 1M tokens | 2026-10-01 |
| [Gemini 4 Argon](https://postcutoff.com/m/gemini-4-argon/) | Google DeepMind | 2026-09-30 | preview | reasoning-llm |  |  |  | $2 in, $10 out per 1M tokens | 2026-10-01 |
| [Praxis-1](https://postcutoff.com/m/praxis-1/) | Runway | 2026-09-30 | preview | robotics |  |  |  | Price not published | 2026-10-03 |
| [AssemblyAI Universal-3.6 Pro Realtime](https://postcutoff.com/m/assemblyai-universal-3-6-pro-realtime/) | AssemblyAI | 2026-09-29 | current | audio/speech | `universal-3-6-pro` |  |  | $0.45 per hour | 2026-09-29 |
| [GPT-6.1 Sol](https://postcutoff.com/m/gpt-6-1-sol/) | OpenAI | 2026-09-29 | current | reasoning-llm | `gpt-6.1-sol` | 2026-04 | 725 | $2 in, $10 out per 1M tokens | 2026-10-02 |
| [Ling 3.1 Flash](https://postcutoff.com/m/ling-3-1-flash/) | inclusionAI (Ant Group) | 2026-09-29 | preview | reasoning-llm | `inclusionai/ling-3.1-flash` |  |  | Free | 2026-10-02 |
| [Claude Sonnet 5.5](https://postcutoff.com/m/claude-sonnet-5-5/) | Anthropic | 2026-09-28 | current | reasoning-llm | `claude-sonnet-5-5` | 2026-06 | 665 | $2 in, $10 out per 1M tokens | 2026-09-29 |
| [Eleven v4 / Eleven v4 Turbo](https://postcutoff.com/m/elevenlabs-v4/) | ElevenLabs | 2026-09-28 | current | audio/speech | `eleven_v4` |  |  | $0.08 per 1K characters | 2026-09-29 |
| [Phonon-2 (open weights, on-device ASR)](https://postcutoff.com/m/phonon-2/) | Fermion Research | 2026-09-28 | current | audio/speech | `FermionResearch/Phonon-2` |  |  | Price not published | 2026-09-30 |
| [Qwen-Audio-3.1-ASR (Flash)](https://postcutoff.com/m/qwen-audio-3-1-asr/) | Alibaba (Qwen) | 2026-09-23 | current | audio/speech | `qwen-audio-3.1-asr-flash-streaming` |  |  | Price not published | 2026-09-29 |
| [Qwen-Audio-3.1-Realtime (Plus)](https://postcutoff.com/m/qwen-audio-3-1-realtime/) | Alibaba (Qwen) | 2026-09-23 | current | audio/speech | `qwen-audio-3.1-realtime-plus` |  |  | $0.80 text in, $6.40 text out per 1M tokens | 2026-09-29 |
| [Claude Opus 5.5](https://postcutoff.com/m/claude-opus-5-5/) | Anthropic | 2026-09-22 | current | reasoning-llm | `claude-opus-5-5` | 2026-06 | 665 | $4 in, $20 out per 1M tokens | 2026-09-29 |
| [Gemini 3.8 Flash TTS](https://postcutoff.com/m/gemini-3-8-flash-tts/) | Google DeepMind | 2026-09-22 | current | audio/speech | `gemini-3.8-flash-tts` |  |  | $0.50 in, $9 out per 1M tokens | 2026-09-29 |
| [GPT-6 Luna](https://postcutoff.com/m/gpt-6-luna/) | OpenAI | 2026-09-22 | current | reasoning-llm | `gpt-6-luna` | 2026-05 | 694 | $0.10 in, $0.50 out per 1M tokens | 2026-10-07 |
| [GPT-6 Sol](https://postcutoff.com/m/gpt-6-sol/) | OpenAI | 2026-09-22 | current | reasoning-llm | `gpt-6-sol` | 2026-04 | 725 | $2 in, $10 out per 1M tokens | 2026-09-29 |
| [Qwen-Audio-3.1-TTS-Next](https://postcutoff.com/m/qwen-audio-3-1-tts-next/) | Alibaba (Qwen) | 2026-09-22 | current | audio/speech | `qwen-audio-3.1-tts-next` |  |  | $0.848 in, $1.696 out per 1M tokens | 2026-09-29 |
| [Grok 4.7](https://postcutoff.com/m/grok-4-7/) | xAI | 2026-09-21 | current | reasoning-llm | `grok-4.7` | 2026-05 | 694 | $2 in, $6 out per 1M tokens | 2026-09-29 |
| [MiMo-V2.6-Flash](https://postcutoff.com/m/mimo-v2-6-flash/) | Xiaomi | 2026-09-21 | current | reasoning-llm | `mimo-v2.6-flash` |  |  | $0.14 in, $0.28 out per 1M tokens | 2026-09-29 |
| [MiMo-V2.6-Pro](https://postcutoff.com/m/mimo-v2-6-pro/) | Xiaomi | 2026-09-21 | current | reasoning-llm | `mimo-v2.6-pro` |  |  | $0.435 in, $0.87 out per 1M tokens | 2026-09-29 |
| [Qwen-Image-2.1](https://postcutoff.com/m/qwen-image-2-1/) | Alibaba (Qwen) | 2026-09-20 | current | image-gen | `Qwen/Qwen-Image-2.1` |  |  | Price not published | 2026-09-30 |
| [Step 5 Preview](https://postcutoff.com/m/step-5-preview/) | StepFun | 2026-09-20 | preview | reasoning-llm | `step-5-preview` |  |  | $1 in, $2.70 out per 1M tokens | 2026-09-29 |
| [Qwen3.8-LiveTranslate (Flash Realtime)](https://postcutoff.com/m/qwen3-8-livetranslate/) | Alibaba (Qwen) | 2026-09-19 | current | audio/speech | `qwen3.8-livetranslate-flash-realtime` |  |  | $7.50 audio in, $20 text out per 1M tokens | 2026-09-29 |
| [Grok Voice Transcribe 2.0](https://postcutoff.com/m/grok-voice-transcribe-2-0/) | xAI | 2026-09-18 | current | audio/speech | `grok-voice-transcribe-2.0` |  |  | $0.10 per hour, batch | 2026-09-29 |
| [Helix 2.5](https://postcutoff.com/m/figure-helix-2-5/) | Figure AI | 2026-09-17 | current | robotics |  |  |  | Price not published |  |
| [Speechmatics Linden 1 (Agent STT)](https://postcutoff.com/m/speechmatics-linden-1/) | Speechmatics | 2026-09-17 | current | audio/speech | `linden-1` |  |  | $0.30 per hour | 2026-09-29 |
| [Gemini 3.8 Live](https://postcutoff.com/m/gemini-3-8-live/) | Google DeepMind | 2026-09-15 | current | audio/speech | `gemini-3.8-live` |  |  | $0.75 in, $4.50 out per 1M tokens | 2026-09-29 |
| [StepAudio 3 ASR Max / StepAudio 3 TTS](https://postcutoff.com/m/stepaudio-3-asr-tts/) | StepFun | 2026-09-15 | current | audio/speech | `stepaudio-3-asr-max` |  |  | $0.40 per hour, speech recognition | 2026-09-29 |
| [StepAudio 3 Realtime](https://postcutoff.com/m/stepaudio-3-realtime/) | StepFun | 2026-09-15 | preview | audio/speech | `stepaudio-3-realtime-preview` |  |  | Free | 2026-09-29 |
| [Eleven Music v2.5](https://postcutoff.com/m/elevenlabs-music-v2-5/) | ElevenLabs | 2026-09-11 | current | music | `music_v2_5` |  |  | $0.15 per minute | 2026-09-29 |
| [DeepSeek-V4.1-Flash](https://postcutoff.com/m/deepseek-v4-1-flash/) | DeepSeek | 2026-09-10 | current | reasoning-llm | `deepseek-flash` |  |  | $0.30 in, $1.20 out per 1M tokens | 2026-09-29 |
| [UnifoLM-WLA-1.0](https://postcutoff.com/m/unifolm-wla-1-0/) | Unitree Robotics | 2026-09-10 | current | robotics | `unitreerobotics/UnifoLM-WLA-1.0-Base` |  |  | Price not published | 2026-09-29 |
| [Suno v6 (v6, v6-wild, v6-mini)](https://postcutoff.com/m/suno-v6/) | Suno | 2026-09-09 | current | music | `v6` |  |  | $10 per month, Pro plan | 2026-09-29 |
| [YuE2-3B](https://postcutoff.com/m/yue2/) | Multimodal Art Projection (M-A-P) | 2026-09-09 | current | music |  |  |  | Price not published | 2026-09-29 |
| [GPT Image 2.5 Flare](https://postcutoff.com/m/gpt-image-2-5-flare/) | OpenAI | 2026-09-08 | current | image-gen | `gpt-image-2.5-flare` |  |  | $5 text in, $30 image out per 1M tokens | 2026-09-29 |
| [GPT Image 2.5 Sunburst](https://postcutoff.com/m/gpt-image-2-5-sunburst/) | OpenAI | 2026-09-08 | current | image-gen | `gpt-image-2.5-sunburst` |  |  | $5 text in, $30 image out per 1M tokens | 2026-09-29 |
| [Mercury 2.5](https://postcutoff.com/m/mercury-2-5/) | Inception | 2026-09-08 | current | reasoning-llm | `mercury-2.5` |  |  | $0.20 in, $0.75 out per 1M tokens | 2026-09-30 |
| [GPT-6 Astra](https://postcutoff.com/m/gpt-6-astra/) | OpenAI | 2026-09-03 | current | reasoning-llm | `gpt-6-astra` | 2026-04 | 725 | $10 in, $50 out per 1M tokens | 2026-09-29 |
| [MAI-Transcribe-2](https://postcutoff.com/m/mai-transcribe-2/) | Microsoft | 2026-09-03 | preview | audio/speech | `MAI-Transcribe-2` |  |  | $0.10 per hour | 2026-09-29 |
| [Muse Voice Transcribe 1.0](https://postcutoff.com/m/muse-voice-transcribe-1-0/) | Meta | 2026-09-03 | current | audio/speech | `muse-voice-transcribe-1.0` |  |  | $3 per 1,000 minutes | 2026-09-29 |
| [Gemini 3.8 Flash](https://postcutoff.com/m/gemini-3-8-flash/) | Google DeepMind | 2026-09-02 | current | reasoning-llm | `gemini-3.8-flash` | 2026-03 | 747 | $0.75 in, $3.75 out per 1M tokens | 2026-09-29 |
| [Muse Spark 1.3](https://postcutoff.com/m/muse-spark-1-3/) | Meta | 2026-09-02 | current | reasoning-llm | `muse-spark-1.3` |  |  | $1.25 in, $4.25 out per 1M tokens | 2026-09-29 |
| [Claude Fable 5.1](https://postcutoff.com/m/claude-fable-5-1/) | Anthropic | 2026-09-01 | current | reasoning-llm | `claude-fable-5-1` | 2026-06 | 665 | $10 in, $50 out per 1M tokens | 2026-09-29 |
| [Claude Mythos 5.1](https://postcutoff.com/m/claude-mythos-5-1/) | Anthropic | 2026-09-01 | current | reasoning-llm | `claude-mythos-5-1` | 2026-06 | 665 | $10 in, $50 out per 1M tokens | 2026-09-29 |
| [Qwen3.8-Omni-Flash](https://postcutoff.com/m/qwen3-8-omni-flash/) | Alibaba (Qwen) | 2026-09 | current | multimodal | `qwen3.8-omni-flash` |  |  | $0.15 in, $0.47 out per 1M tokens | 2026-09-29 |
| [Inworld Realtime TTS-2 / TTS-2 Flash](https://postcutoff.com/m/inworld-tts-2/) | Inworld AI | 2026-08-31 | current | audio/speech | `inworld-tts-2` |  |  | $25 per 1M characters | 2026-09-29 |
| [Cartesia Sonic-3.6](https://postcutoff.com/m/cartesia-sonic-3-6/) | Cartesia | 2026-08-27 | current | audio/speech | `sonic-3.6` |  |  | $0.037 per 1K characters | 2026-09-29 |
| [Gemini 3.5 Transcribe (and Transcribe Live)](https://postcutoff.com/m/gemini-3-5-transcribe/) | Google DeepMind | 2026-08-26 | current | audio/speech | `gemini-3.5-transcribe` |  |  | $2 audio in, $12 out per 1M tokens | 2026-09-29 |
| [Breeze TTS 2](https://postcutoff.com/m/breeze-tts-2/) | BreezeBlue | 2026-08-25 | current | audio/speech | `BreezeBlue/Breeze-TTS-2` |  |  | Price not published | 2026-09-29 |
| [Skild S1 (Skild Brain)](https://postcutoff.com/m/skild-s1/) | Skild AI | 2026-08-25 | current | robotics |  |  |  | Price not published |  |
| [Eleven v3 Conversational](https://postcutoff.com/m/elevenlabs-v3-conversational/) | ElevenLabs | 2026-08-19 | current | audio/speech | `eleven_v3_conversational` |  |  | $0.04 per 1K characters | 2026-09-29 |
| [Generalist GEN-1.5](https://postcutoff.com/m/generalist-gen-1-5/) | Generalist AI | 2026-08-19 | current | robotics |  |  |  | Price not published |  |
| [TeleOCR (ex NaviDC-OCR)](https://postcutoff.com/m/teleocr/) | TeleAI | 2026-08-17 | current | multimodal |  |  |  | Price not published | 2026-10-06 |
| [Gemini 3.7 Flash](https://postcutoff.com/m/gemini-3-7-flash/) | Google DeepMind | 2026-08-13 | legacy | reasoning-llm | `gemini-3.7-flash` |  |  | $0.75 in, $3.75 out per 1M tokens | 2026-09-29 |
| [Deepgram Flux TTS](https://postcutoff.com/m/deepgram-flux-tts/) | Deepgram | 2026-08-12 | current | audio/speech | `flux-haley-en` |  |  | $0.045 per 1K characters | 2026-09-29 |
| [LTX-2.5](https://postcutoff.com/m/ltx-2-5/) | Lightricks | 2026-08-11 | current | video-gen |  |  |  | $0.09 per second, fast | 2026-10-03 |
| [NVIDIA Nemotron 3.5 Lightning (30B-A3B)](https://postcutoff.com/m/nemotron-3-5-lightning/) | NVIDIA | 2026-08-11 | current | llm | `nvidia/nemotron-3.5-lightning-30b-a3b` | 2025-09 | 834 | $0.06 in, $0.16 out per 1M tokens | 2026-09-29 |
| [DYNA-2 (World-Action Model)](https://postcutoff.com/m/dyna-2/) | Dyna Robotics | 2026-08-10 | current | robotics |  |  |  | Price not published |  |
| [Soniox TTS v2](https://postcutoff.com/m/soniox-tts-v2/) | Soniox | 2026-08-10 | current | audio/speech | `tts-rt-v2` |  |  | $4 in, $21.50 out per 1M tokens | 2026-09-29 |
| [Grok Imagine Image 2.0](https://postcutoff.com/m/grok-imagine-image-2/) | xAI | 2026-08-07 | current | image-gen | `grok-imagine-image-2.0` |  |  | $0.04 per image | 2026-09-29 |
| [Qwen3.8-27B](https://postcutoff.com/m/qwen3-8-27b/) | Alibaba (Qwen) | 2026-08-05 | current | multimodal | `qwen/qwen3.8-27b` |  |  | Price not published | 2026-09-29 |
| [SeedRealtime (Doubao realtime audio-visual model)](https://postcutoff.com/m/seedrealtime/) | ByteDance | 2026-08-05 | current | audio/speech |  |  |  | Price not published |  |
| [NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B)](https://postcutoff.com/m/nemotron-voicechat/) | NVIDIA | 2026-08-03 | current | audio/speech | `nvidia/NVIDIA-NemotronLabs-VoiceChat-11B` |  |  | Price not published | 2026-09-29 |
| [GLM-5.3](https://postcutoff.com/m/glm-5-3/) | Zhipu AI (Z.ai) | 2026-08 | current | reasoning-llm | `glm-5.3` |  |  | $1.40 in, $4.40 out per 1M tokens | 2026-09-29 |
| [GLM-5.3-Flash / FlashX](https://postcutoff.com/m/glm-5-3-flash/) | Zhipu AI (Z.ai) | 2026-08 | current | multimodal | `glm-5.3-flash` |  |  | $0.15 in, $0.50 out per 1M tokens | 2026-09-30 |
| [Muse Glimmer 30B](https://postcutoff.com/m/muse-glimmer-30b/) | Meta | 2026-08 | current | llm | `meta/muse-glimmer-30b` | 2026-01 | 793 | $0.30 in, $1.20 out per 1M tokens | 2026-09-29 |
| [Qwen3.8-Flash](https://postcutoff.com/m/qwen3-8-flash/) | Alibaba (Qwen) | 2026-08 | current | reasoning-llm | `qwen3.8-flash` |  |  | $0.15 in, $0.47 out per 1M tokens | 2026-09-29 |
| [Qwen3.8-Max](https://postcutoff.com/m/qwen3-8-max/) | Alibaba (Qwen) | 2026-08 | current | reasoning-llm | `qwen3.8-max` |  |  | $2 in, $6 out per 1M tokens | 2026-09-29 |
| [MiniMax H3](https://postcutoff.com/m/minimax-h3/) | MiniMax | 2026-07-31 | current | video-gen | `MiniMax-H3` |  |  | $0.08 per second, 768p | 2026-09-29 |
| [Gemini Robotics 2](https://postcutoff.com/m/gemini-robotics-2/) | Google DeepMind | 2026-07-30 | preview | robotics |  |  |  | Price not published | 2026-09-29 |
| [Gemini Robotics ER 2](https://postcutoff.com/m/gemini-robotics-er-2/) | Google DeepMind | 2026-07-30 | preview | robotics | `gemini-robotics-er-2-preview` |  |  | $1 in, $5 out per 1M tokens | 2026-09-29 |
| [Gemini Robotics On-Device 2](https://postcutoff.com/m/gemini-robotics-on-device-2/) | Google DeepMind | 2026-07-30 | preview | robotics |  |  |  | Price not published | 2026-09-29 |
| [Grok Voice Think Fast 2.0](https://postcutoff.com/m/grok-voice-think-fast-2-0/) | xAI | 2026-07-29 | current | audio/speech | `grok-voice-think-fast-2.0` |  |  | $0.08 per minute | 2026-09-29 |
| [Lyria 3.5](https://postcutoff.com/m/lyria-3-5/) | Google DeepMind | 2026-07-29 | current | music | `lyria-3.5` |  |  | $0.08 per song | 2026-09-29 |
| [GPT-Live-Transcribe](https://postcutoff.com/m/gpt-live-transcribe/) | OpenAI | 2026-07-28 | current | audio/speech | `gpt-live-transcribe` |  |  | $0.017 per minute | 2026-09-29 |
| [GPT-Transcribe](https://postcutoff.com/m/gpt-transcribe/) | OpenAI | 2026-07-28 | current | audio/speech | `gpt-transcribe` |  |  | $0.0045 per minute | 2026-09-29 |
| [Claude Opus 5](https://postcutoff.com/m/claude-opus-5/) | Anthropic | 2026-07-24 | legacy | reasoning-llm | `claude-opus-5` | 2026-05 | 694 | $5 in, $25 out per 1M tokens | 2026-09-29 |
| [Midjourney V8.2](https://postcutoff.com/m/midjourney-v8-2/) | Midjourney | 2026-07-24 | current | image-gen |  |  |  | Price not published | 2026-09-29 |
| [FLUX 3](https://postcutoff.com/m/flux-3/) | Black Forest Labs | 2026-07-23 | preview | video-gen | `flux-3-video` |  |  | $0.17 per second | 2026-09-29 |
| [Gemini 3.5 Flash-Lite](https://postcutoff.com/m/gemini-3-5-flash-lite/) | Google DeepMind | 2026-07-21 | current | llm | `gemini-3.5-flash-lite` |  |  | $0.30 in, $2.50 out per 1M tokens | 2026-09-29 |
| [Gemini 3.6 Flash](https://postcutoff.com/m/gemini-3-6-flash/) | Google DeepMind | 2026-07-21 | legacy | reasoning-llm | `gemini-3.6-flash` |  |  | $0.75 in, $3.75 out per 1M tokens | 2026-09-29 |
| [Qwen-Image-3.0 (Pro)](https://postcutoff.com/m/qwen-image-3-0/) | Alibaba (Qwen) | 2026-07-21 | current | image-gen | `qwen-image-3.0-pro` |  |  | $0.04 per image | 2026-09-29 |
| [Qwen-Audio-3.0-TTS (Flash / Plus)](https://postcutoff.com/m/qwen-audio-3-0-tts/) | Alibaba (Qwen / Tongyi Lab) | 2026-07-20 | current | audio/speech | `qwen-audio-3.0-tts-flash` |  |  | $27.59 per 1M characters | 2026-09-29 |
| [Seed Audio 1.0](https://postcutoff.com/m/seed-audio-1-0/) | ByteDance | 2026-07-20 | current | audio/speech |  |  |  | Price not published |  |
| [Kimi K3](https://postcutoff.com/m/kimi-k3/) | Moonshot AI | 2026-07-16 | current | reasoning-llm | `kimi-k3` |  |  | $3 in, $15 out per 1M tokens | 2026-09-29 |
| [MiniMax Music 3.0](https://postcutoff.com/m/minimax-music-3/) | MiniMax | 2026-07-16 | current | music | `music-3.0` |  |  | $0.15 per song | 2026-09-29 |
| [Mistral OCR 4.1](https://postcutoff.com/m/mistral-ocr-4-1/) | Mistral AI | 2026-07-16 | current | multimodal | `mistral-ocr-4-1` |  |  | $4 per 1,000 pages | 2026-09-29 |
| [Xiaomi-Robotics-1 (XR-1, 5B)](https://postcutoff.com/m/xiaomi-robotics-1/) | Xiaomi | 2026-07-16 | current | robotics | `XiaomiRobotics/Xiaomi-Robotics-1-5B` |  |  | Price not published | 2026-09-29 |
| [Xiaomi-Robotics-U0 (38B) / U0-4B](https://postcutoff.com/m/xiaomi-robotics-u0/) | Xiaomi | 2026-07-13 | current | world-model | `XiaomiRobotics/Xiaomi-Robotics-U0` |  |  | Price not published | 2026-09-29 |
| [Cartesia Ink-2 (streaming STT)](https://postcutoff.com/m/cartesia-ink-2/) | Cartesia | 2026-07-09 | current | audio/speech | `ink-2` |  |  | Price not published | 2026-09-29 |
| [GPT-5.6 Luna](https://postcutoff.com/m/gpt-5-6-luna/) | OpenAI | 2026-07-09 | legacy | reasoning-llm | `gpt-5.6-luna` | 2026-02 | 769 | $0.20 in, $1.20 out per 1M tokens | 2026-09-29 |
| [GPT-5.6 Sol](https://postcutoff.com/m/gpt-5-6-sol/) | OpenAI | 2026-07-09 | legacy | reasoning-llm | `gpt-5.6-sol` | 2026-02 | 769 | $4 in, $20 out per 1M tokens | 2026-09-29 |
| [GPT-5.6 Terra](https://postcutoff.com/m/gpt-5-6-terra/) | OpenAI | 2026-07-09 | current | reasoning-llm | `gpt-5.6-terra` | 2026-02 | 769 | $2 in, $12 out per 1M tokens | 2026-09-29 |
| [GPT-Live 1](https://postcutoff.com/m/gpt-live-1/) | OpenAI | 2026-07-08 | current | audio/speech | `gpt-live-1` | 2025-07 | 853 | $0.05 per minute | 2026-09-29 |
| [Robostral Navigate](https://postcutoff.com/m/robostral-navigate/) | Mistral AI | 2026-07-08 | preview | robotics |  |  |  | Price not published | 2026-09-29 |
| [AssemblyAI Universal-3.5 Pro (async)](https://postcutoff.com/m/assemblyai-universal-3-5-pro/) | AssemblyAI | 2026-07-07 | current | audio/speech | `universal-3-pro` |  |  | $0.21 per hour | 2026-09-29 |
| [Speechify Simba 3.2](https://postcutoff.com/m/speechify-simba-3-2/) | Speechify (SpeechifyAI) | 2026-07-07 | current | audio/speech |  |  |  | $10 per 1M characters | 2026-09-29 |
| [GPT-Realtime-2.1](https://postcutoff.com/m/gpt-realtime-2-1/) | OpenAI | 2026-07-06 | current | audio/speech | `gpt-realtime-2.1` | 2024-09 | 897 | $4 text in, $24 text out per 1M tokens | 2026-09-29 |
| [Leanstral 1.5](https://postcutoff.com/m/leanstral-1-5/) | Mistral AI | 2026-07-02 | current | code | `leanstral-1-5` |  |  | Free | 2026-10-01 |
| [Mureka V9.5 (and O3)](https://postcutoff.com/m/mureka-9-5/) | Kunlun Tech (Skywork AI) | 2026-07 | current | music | `mureka-9.5` |  |  | Price not published | 2026-09-29 |
| [Claude Sonnet 5](https://postcutoff.com/m/claude-sonnet-5/) | Anthropic | 2026-06-30 | legacy | reasoning-llm | `claude-sonnet-5` | 2026-01 | 793 | $2 in, $10 out per 1M tokens | 2026-09-29 |
| [Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image)](https://postcutoff.com/m/gemini-3-1-flash-lite-image/) | Google DeepMind | 2026-06-30 | current | image-gen | `gemini-3.1-flash-lite-image` |  |  | $0.25 in, $1.50 out per 1M tokens | 2026-09-29 |
| [Speechmatics Melia 1 (multilingual STT)](https://postcutoff.com/m/speechmatics-melia-1/) | Speechmatics | 2026-06-17 | preview | audio/speech | `melia-1` |  |  | $0.129 per hour | 2026-09-29 |
| [Soniox v5 (Async and Real-Time STT)](https://postcutoff.com/m/soniox-stt-v5/) | Soniox | 2026-06-11 | current | audio/speech | `stt-async-v5` |  |  | $1.50 in, $3.50 out per 1M tokens | 2026-09-29 |
| [Claude Fable 5](https://postcutoff.com/m/claude-fable-5/) | Anthropic | 2026-06-09 | legacy | reasoning-llm | `claude-fable-5` | 2026-01 | 793 | $10 in, $50 out per 1M tokens | 2026-09-29 |
| [Gemini 3.5 Live Translate](https://postcutoff.com/m/gemini-3-5-live-translate/) | Google DeepMind | 2026-06-09 | preview | audio/speech | `gemini-3.5-live-translate-preview` |  |  | $3.50 audio in, $21 audio out per 1M tokens | 2026-09-29 |
| [Luma Ray3.2](https://postcutoff.com/m/luma-ray-3-2/) | Luma AI | 2026-06-09 | current | video-gen | `ray-3.2` |  |  | Price not published | 2026-09-29 |
| [Boson AI Higgs Audio v3 (Higgs TTS 3 4B / Higgs STT 3)](https://postcutoff.com/m/higgs-audio-v3/) | Boson AI | 2026-06-04 | current | audio/speech | `bosonai/higgs-audio-v3-tts-4b` |  |  | Price not published | 2026-09-29 |
| [NVIDIA Nemotron 3 Ultra (550B-A55B)](https://postcutoff.com/m/nemotron-3-ultra/) | NVIDIA | 2026-06-04 | current | reasoning-llm | `nvidia/nemotron-3-ultra-550b-a55b` | 2025-09 | 834 | $0.60 in, $2.40 out per 1M tokens | 2026-09-29 |
| [Ideogram 4.0](https://postcutoff.com/m/ideogram-4/) | Ideogram | 2026-06-03 | current | image-gen | `ideogram-v4` |  |  | Price not published | 2026-09-29 |
| [MAI-Voice-2 / MAI-Voice-2-Flash](https://postcutoff.com/m/mai-voice-2/) | Microsoft | 2026-06-02 | preview | audio/speech | `en-US-Harper:MAI-Voice-2` |  |  | $22 per 1M characters | 2026-09-29 |
| [Cosmos 3 (Nano / Super)](https://postcutoff.com/m/cosmos-3/) | NVIDIA | 2026-06-01 | current | world-model | `nvidia/Cosmos3-Nano` |  |  | Price not published | 2026-09-29 |
| [MiniMax-M3](https://postcutoff.com/m/minimax-m3/) | MiniMax | 2026-06-01 | current | reasoning-llm | `MiniMax-M3` |  |  | $0.30 in, $1.20 out per 1M tokens | 2026-09-29 |
| [Kimi K2.7 Code](https://postcutoff.com/m/kimi-k2-7-code/) | Moonshot AI | 2026-06 | current | code | `kimi-k2.7-code` |  |  | $0.95 in, $4 out per 1M tokens | 2026-09-29 |
| [VUI Labs Luna-TTS (and Luna-TTS Realtime)](https://postcutoff.com/m/vui-luna-tts/) | VUI Labs | 2026-06 | current | audio/speech |  |  |  | $15 per 1M characters | 2026-09-29 |
| [Grok Imagine Video 1.5](https://postcutoff.com/m/grok-imagine-video-1-5/) | xAI | 2026-05-30 | current | video-gen | `grok-imagine-video-1.5` |  |  | $0.08 per second | 2026-09-29 |
| [Claude Opus 4.8](https://postcutoff.com/m/claude-opus-4-8/) | Anthropic | 2026-05-28 | legacy | reasoning-llm | `claude-opus-4-8` | 2026-01 | 793 | $5 in, $25 out per 1M tokens | 2026-09-29 |
| [Eleven Dubbing v2](https://postcutoff.com/m/elevenlabs-dubbing-v2/) | ElevenLabs | 2026-05-28 | preview | audio/speech |  |  |  | $2.20 per minute | 2026-09-29 |
| [Qwen3.7-Plus](https://postcutoff.com/m/qwen3-7-plus/) | Alibaba (Qwen) | 2026-05-26 | current | reasoning-llm | `qwen3.7-plus` |  |  | $0.40 in, $1.60 out per 1M tokens | 2026-09-29 |
| [Runway Aleph 2.0](https://postcutoff.com/m/runway-aleph-2/) | Runway | 2026-05-21 | current | video-gen | `aleph2` |  |  | $0.28 per second | 2026-09-29 |
| [Command A+](https://postcutoff.com/m/command-a-plus/) | Cohere | 2026-05-20 | current | reasoning-llm | `command-a-plus-05-2026` |  |  | $0.30 in, $1.50 out per 1M tokens | 2026-09-29 |
| [Stable Audio 3.0](https://postcutoff.com/m/stable-audio-3/) | Stability AI | 2026-05-20 | current | music |  |  |  | Price not published | 2026-09-29 |
| [Gemini 3.5 Flash](https://postcutoff.com/m/gemini-3-5-flash/) | Google DeepMind | 2026-05-19 | legacy | reasoning-llm | `gemini-3.5-flash` |  |  | $1.50 in, $9 out per 1M tokens | 2026-09-29 |
| [Recraft V4.1](https://postcutoff.com/m/recraft-v4-1/) | Recraft | 2026-05-14 | current | image-gen | `recraftv4_1` |  |  | $0.035 per image | 2026-09-29 |
| [Gemini 3.1 Flash-Lite](https://postcutoff.com/m/gemini-3-1-flash-lite/) | Google DeepMind | 2026-05-07 | deprecated | llm | `gemini-3.1-flash-lite` |  |  | $0.25 in, $1.50 out per 1M tokens | 2026-09-29 |
| [GPT-Realtime-2](https://postcutoff.com/m/gpt-realtime-2/) | OpenAI | 2026-05-07 | current | audio/speech | `gpt-realtime-2` | 2024-09 | 897 | $4 text in, $24 text out per 1M tokens | 2026-09-29 |
| [GPT-Realtime-Translate](https://postcutoff.com/m/gpt-realtime-translate/) | OpenAI | 2026-05-07 | current | audio/speech | `gpt-realtime-translate` |  |  | $0.034 per minute | 2026-09-29 |
| [GPT-Realtime-Whisper](https://postcutoff.com/m/gpt-realtime-whisper/) | OpenAI | 2026-05-07 | legacy | audio/speech | `gpt-realtime-whisper` |  |  | $0.017 per minute | 2026-09-29 |
| [MolmoAct 2 / MolmoAct 2-Think](https://postcutoff.com/m/molmoact-2/) | Ai2 (Allen Institute for AI) | 2026-05-05 | current | robotics | `allenai/MolmoAct2` |  |  | Price not published | 2026-09-29 |
| [Gemini Omni Flash (Omni 1.1 Flash)](https://postcutoff.com/m/gemini-omni-flash/) | Google DeepMind | 2026-05 | current | video-gen | `gemini-omni-1.1-flash` |  |  | $1.50 in, $9 out per 1M tokens | 2026-09-29 |
| [Grok Build 0.1](https://postcutoff.com/m/grok-build-0-1/) | xAI | 2026-05 | current | code | `grok-build-0.1` |  |  | $1 in, $2 out per 1M tokens | 2026-09-29 |
| [Mistral Medium 3.5](https://postcutoff.com/m/mistral-medium-3-5/) | Mistral AI | 2026-04-28 | current | multimodal | `mistral-medium-3-5` |  |  | $1.50 in, $7.50 out per 1M tokens | 2026-09-29 |
| [NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning)](https://postcutoff.com/m/nemotron-3-nano-omni/) | NVIDIA | 2026-04-28 | current | multimodal | `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` |  |  | Price not published | 2026-09-29 |
| [DeepSeek-V4-Pro](https://postcutoff.com/m/deepseek-v4-pro/) | DeepSeek | 2026-04-24 | current | reasoning-llm | `deepseek-v4-pro` |  |  | $1.32 in, $3.96 out per 1M tokens | 2026-09-29 |
| [GPT-5.5](https://postcutoff.com/m/gpt-5-5/) | OpenAI | 2026-04-24 | legacy | reasoning-llm | `gpt-5.5` | 2025-12 | 809 | $5 in, $30 out per 1M tokens | 2026-09-29 |
| [GPT-5.5 Pro](https://postcutoff.com/m/gpt-5-5-pro/) | OpenAI | 2026-04-24 | legacy | reasoning-llm | `gpt-5.5-pro` | 2025-12 | 809 | $30 in, $180 out per 1M tokens | 2026-09-29 |
| [Gemini Embedding 2](https://postcutoff.com/m/gemini-embedding-2/) | Google DeepMind | 2026-04-22 | current | embedding | `gemini-embedding-2` |  |  | $0.20 in per 1M tokens | 2026-09-29 |
| [GPT Image 2](https://postcutoff.com/m/gpt-image-2/) | OpenAI | 2026-04-21 | legacy | image-gen | `gpt-image-2` |  |  | $5 text in, $30 image out per 1M tokens | 2026-09-29 |
| [GPT-Rosalind](https://postcutoff.com/m/gpt-rosalind/) | OpenAI | 2026-04-17 | current | reasoning-llm | `gpt-rosalind-research` |  |  | $5 in, $25 out per 1M tokens | 2026-10-05 |
| [Grok Text to Speech (Grok TTS API)](https://postcutoff.com/m/grok-tts/) | xAI | 2026-04-17 | current | audio/speech |  |  |  | $15 per 1M characters | 2026-09-29 |
| [Isaac GR00T N1.7](https://postcutoff.com/m/gr00t-n1-7/) | NVIDIA | 2026-04-17 | current | robotics | `nvidia/GR00T-N1.7-3B` |  |  | Price not published | 2026-09-29 |
| [Claude Opus 4.7](https://postcutoff.com/m/claude-opus-4-7/) | Anthropic | 2026-04-16 | legacy | reasoning-llm | `claude-opus-4-7` | 2026-01 | 793 | $5 in, $25 out per 1M tokens | 2026-09-29 |
| [π0.7](https://postcutoff.com/m/pi-0-7/) | Physical Intelligence | 2026-04-16 | current | robotics |  |  |  | Price not published | 2026-09-29 |
| [Gemini 3.1 Flash TTS (preview)](https://postcutoff.com/m/gemini-3-1-flash-tts/) | Google DeepMind | 2026-04-15 | legacy | audio/speech | `gemini-3.1-flash-tts-preview` |  |  | $1 in, $20 out per 1M tokens | 2026-09-29 |
| [AgiBot GO-2 (Genie Operator-2)](https://postcutoff.com/m/agibot-go-2/) | AgiBot | 2026-04-09 | current | robotics |  |  |  | Price not published |  |
| [Gemma 4](https://postcutoff.com/m/gemma-4/) | Google DeepMind | 2026-04-02 | current | llm | `google/gemma-4-31B-it` |  |  | $0.09 in, $0.34 out per 1M tokens | 2026-09-29 |
| [Generalist GEN-1](https://postcutoff.com/m/generalist-gen-1/) | Generalist AI | 2026-04-02 | current | robotics |  |  |  | Price not published |  |
| [Grok 4.3](https://postcutoff.com/m/grok-4-3/) | xAI | 2026-04 | current | reasoning-llm | `grok-4.3` |  |  | $1.25 in, $2.50 out per 1M tokens | 2026-09-29 |
| [Kimi K2.6](https://postcutoff.com/m/kimi-k2-6/) | Moonshot AI | 2026-04 | current | multimodal | `kimi-k2.6` |  |  | $0.95 in, $4 out per 1M tokens | 2026-09-29 |
| [Gemini 3.1 Flash Live (preview)](https://postcutoff.com/m/gemini-3-1-flash-live/) | Google DeepMind | 2026-03-26 | legacy | audio/speech | `gemini-3.1-flash-live-preview` |  |  | $0.75 in, $4.50 out per 1M tokens | 2026-09-29 |
| [Suno v5.5](https://postcutoff.com/m/suno-v5-5/) | Suno | 2026-03-26 | retired | music |  |  |  | Price not published | 2026-09-29 |
| [Voxtral TTS](https://postcutoff.com/m/voxtral-tts/) | Mistral AI | 2026-03-23 | current | audio/speech | `voxtral-tts-2603` |  |  | $0.016 per 1K characters | 2026-09-29 |
| [MiniMax-M2.7](https://postcutoff.com/m/minimax-m2-7/) | MiniMax | 2026-03-18 | current | reasoning-llm | `MiniMax-M2.7` |  |  | $0.30 in, $1.20 out per 1M tokens | 2026-09-29 |
| [Isaac GR00T N2](https://postcutoff.com/m/gr00t-n2/) | NVIDIA | 2026-03-16 | preview | robotics |  |  |  | Price not published | 2026-09-29 |
| [Mistral Small 4](https://postcutoff.com/m/mistral-small-4/) | Mistral AI | 2026-03-16 | current | reasoning-llm | `mistral-small-2603` |  |  | $0.15 in, $0.60 out per 1M tokens | 2026-09-29 |
| [NVIDIA Nemotron 3 Super (120B-A12B)](https://postcutoff.com/m/nemotron-3-super/) | NVIDIA | 2026-03-11 | current | reasoning-llm | `nvidia/nemotron-3-super-120b-a12b` | 2025-06 | 860 | $0.08 in, $0.45 out per 1M tokens | 2026-09-29 |
| [Fish Audio S2 Pro / S2.1 Pro](https://postcutoff.com/m/fish-audio-s2/) | Fish Audio | 2026-03-09 | current | audio/speech | `s2.1-pro` |  |  | $15 per 1M UTF-8 bytes | 2026-09-29 |
| [GPT-5.4](https://postcutoff.com/m/gpt-5-4/) | OpenAI | 2026-03-05 | legacy | reasoning-llm | `gpt-5.4` | 2025-08 | 846 | $2.50 in, $15 out per 1M tokens | 2026-09-29 |
| [Phi-4-Reasoning-Vision-15B](https://postcutoff.com/m/phi-4-reasoning-vision-15b/) | Microsoft | 2026-03-04 | current | multimodal |  |  |  | Price not published | 2026-09-29 |
| [SongGeneration 2 (LeVo 2)](https://postcutoff.com/m/songgeneration-2/) | Tencent AI Lab | 2026-03-01 | current | music |  |  |  | Price not published |  |
| [Grok 4.20 (Reasoning / Non-reasoning / Multi-Agent)](https://postcutoff.com/m/grok-4-20/) | xAI | 2026-03 | legacy | reasoning-llm | `grok-4.20-0309-reasoning` |  |  | $1.25 in, $2.50 out per 1M tokens | 2026-09-29 |
| [Nano Banana 2 (Gemini 3.1 Flash Image)](https://postcutoff.com/m/gemini-3-1-flash-image/) | Google DeepMind | 2026-02-26 | deprecated | image-gen | `gemini-3.1-flash-image` |  |  | $0.50 in, $3 out per 1M tokens | 2026-10-07 |
| [GPT-Audio-1.5 (and gpt-audio / gpt-audio-mini)](https://postcutoff.com/m/gpt-audio-1-5/) | OpenAI | 2026-02-23 | current | audio/speech | `gpt-audio-1.5` | 2024-09 | 897 | $2.50 text in, $10 text out per 1M tokens | 2026-09-29 |
| [GPT-Realtime-1.5](https://postcutoff.com/m/gpt-realtime-1-5/) | OpenAI | 2026-02-23 | legacy | audio/speech | `gpt-realtime-1.5` | 2024-09 | 897 | $4 text in, $16 text out per 1M tokens | 2026-09-29 |
| [Gemini 3.1 Pro](https://postcutoff.com/m/gemini-3-1-pro/) | Google DeepMind | 2026-02-19 | preview | reasoning-llm | `gemini-3.1-pro-preview` |  |  | $2 in, $12 out per 1M tokens | 2026-09-29 |
| [Lyria 3 (Clip / Pro)](https://postcutoff.com/m/lyria-3/) | Google DeepMind | 2026-02-18 | legacy | music | `lyria-3-clip-preview` |  |  | $0.04 per clip | 2026-09-29 |
| [Claude Sonnet 4.6](https://postcutoff.com/m/claude-sonnet-4-6/) | Anthropic | 2026-02-17 | legacy | reasoning-llm | `claude-sonnet-4-6` | 2025-08 | 846 | $3 in, $15 out per 1M tokens | 2026-09-29 |
| [Xiaomi-Robotics-0 (4.7B VLA)](https://postcutoff.com/m/xiaomi-robotics-0/) | Xiaomi | 2026-02-12 | legacy | robotics | `XiaomiRobotics/Xiaomi-Robotics-0-Pretrain` |  |  | Price not published | 2026-09-29 |
| [Claude Opus 4.6](https://postcutoff.com/m/claude-opus-4-6/) | Anthropic | 2026-02-05 | legacy | reasoning-llm | `claude-opus-4-6` | 2025-05 | 863 | $5 in, $25 out per 1M tokens | 2026-09-29 |
| [GPT-5.3-Codex](https://postcutoff.com/m/gpt-5-3-codex/) | OpenAI | 2026-02-05 | current | code | `gpt-5.3-codex` | 2025-08 | 846 | $1.75 in, $14 out per 1M tokens | 2026-09-29 |
| [Rime Arcana v3 / v3 Turbo](https://postcutoff.com/m/rime-arcana-v3/) | Rime | 2026-02-04 | current | audio/speech | `arcana` |  |  | Price not published | 2026-09-29 |
| [Voxtral Transcribe 2 (Mini Transcribe V2 + Voxtral Realtime)](https://postcutoff.com/m/voxtral-transcribe-2/) | Mistral AI | 2026-02-04 | current | audio/speech | `voxtral-mini-2602` |  |  | $0.003 per minute, batch | 2026-09-29 |
| [Kling 3.0 (VIDEO 3.0 / 3.0 Omni)](https://postcutoff.com/m/kling-3-0/) | Kuaishou | 2026-02 | current | video-gen | `fal-ai/kling-video/v3/standard/text-to-video` |  |  | Price not published |  |
| [Qwen3-ASR (0.6B / 1.7B) + Qwen3-ForcedAligner](https://postcutoff.com/m/qwen3-asr/) | Alibaba (Qwen) | 2026-01-29 | current | audio/speech | `Qwen/Qwen3-ASR-1.7B` |  |  | Price not published | 2026-09-29 |
| [ACE-Step 1.5 (incl. 1.5 XL)](https://postcutoff.com/m/ace-step-1-5/) | ACE Studio & StepFun | 2026-01-28 | current | music |  |  |  | Price not published | 2026-09-29 |
| [Helix 02](https://postcutoff.com/m/figure-helix-02/) | Figure AI | 2026-01-27 | legacy | robotics |  |  |  | Price not published |  |
| [MiniMax Speech 2.8 (HD / Turbo)](https://postcutoff.com/m/minimax-speech-2-8/) | MiniMax | 2026-01-23 | current | audio/speech | `speech-2.8-hd` |  |  | $100 per 1M characters, HD | 2026-09-29 |
| [Qwen3-TTS (open weights 0.6B / 1.7B; API qwen3-tts-flash)](https://postcutoff.com/m/qwen3-tts/) | Alibaba (Qwen) | 2026-01-22 | current | audio/speech | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` |  |  | Price not published | 2026-09-29 |
| [FLUX.2 [klein] (4B / 9B)](https://postcutoff.com/m/flux-2-klein/) | Black Forest Labs | 2026-01-14 | current | image-gen | `flux-2-klein-4b` |  |  | $0.014 per image | 2026-09-29 |
| [Kyutai Pocket TTS](https://postcutoff.com/m/kyutai-pocket-tts/) | Kyutai | 2026-01-13 | current | audio/speech | `kyutai/pocket-tts` |  |  | Price not published | 2026-09-29 |
| [1X World Model (1XWM)](https://postcutoff.com/m/1x-world-model/) | 1X Technologies | 2026-01-12 | preview | world-model |  |  |  | Price not published |  |
| [Scribe v2 / Scribe v2 Medical](https://postcutoff.com/m/elevenlabs-scribe-v2/) | ElevenLabs | 2026-01-09 | current | audio/speech | `scribe_v2` |  |  | $0.22 per hour | 2026-09-29 |
| [UnifoLM-VLA-0 (and UnifoLM-WMA-0)](https://postcutoff.com/m/unifolm-vla-0/) | Unitree Robotics | 2026-01 | legacy | robotics | `unitreerobotics/UnifoLM-VLA-Base` |  |  | Price not published | 2026-09-29 |
| [Cosmos Reason 2](https://postcutoff.com/m/cosmos-reason-2/) | NVIDIA | 2025-12-19 | current | multimodal | `nvidia/Cosmos-Reason2-8B` |  |  | Price not published | 2026-09-29 |
| [Cohere Rerank 4 (Pro / Fast)](https://postcutoff.com/m/cohere-rerank-4/) | Cohere | 2025-12-11 | current | embedding | `rerank-v4.0-pro` |  |  | Price not published | 2026-09-29 |
| [Fun-CosyVoice3 0.5B (2512) + Fun-ASR-Nano + Fun-Audio-Chat-8B](https://postcutoff.com/m/fun-cosyvoice3/) | Alibaba (Tongyi Lab / FunAudioLLM) | 2025-12-11 | current | audio/speech | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` |  |  | Price not published | 2026-09-29 |
| [NVIDIA MagpieTTS Multilingual 357M](https://postcutoff.com/m/nvidia-magpie-tts-multilingual/) | NVIDIA | 2025-12-11 | current | audio/speech | `nvidia/magpie_tts_multilingual_357m` |  |  | Price not published | 2026-09-29 |
| [Amazon Nova 2 Lite](https://postcutoff.com/m/nova-2-lite/) | Amazon | 2025-12-02 | current | reasoning-llm | `amazon.nova-2-lite-v1:0` | 2025-10 | 826 | $0.30 in, $2.50 out per 1M tokens | 2026-09-29 |
| [Amazon Nova 2 Sonic](https://postcutoff.com/m/nova-2-sonic/) | Amazon | 2025-12-02 | current | audio/speech | `amazon.nova-2-sonic-v1:0` |  |  | $0.33 text in, $2.75 text out per 1M tokens | 2026-09-29 |
| [Mistral Large 3](https://postcutoff.com/m/mistral-large-3/) | Mistral AI | 2025-12-02 | current | multimodal | `mistral-large-2512` |  |  | $0.50 in, $1.50 out per 1M tokens | 2026-09-29 |
| [DeepSeek-V3.2](https://postcutoff.com/m/deepseek-v3-2/) | DeepSeek | 2025-12-01 | legacy | reasoning-llm | `deepseek-chat / deepseek-reasoner (no longer serve V3.2)` |  |  | Price not published | 2026-09-29 |
| [Runway Gen-4.5](https://postcutoff.com/m/runway-gen-4-5/) | Runway | 2025-12-01 | current | video-gen | `gen4.5` |  |  | $0.12 per second | 2026-09-29 |
| [FLUX.2 [max]](https://postcutoff.com/m/flux-2-max/) | Black Forest Labs | 2025-12 | current | image-gen | `flux-2-max` |  |  | $0.07 per image | 2026-09-29 |
| [GLM-4.6V](https://postcutoff.com/m/glm-4-6v/) | Zhipu AI (Z.ai) | 2025-12 | legacy | multimodal | `glm-4.6v` |  |  | $0.30 in, $0.90 out per 1M tokens |  |
| [DeepSeekMath-V2](https://postcutoff.com/m/deepseekmath-v2/) | DeepSeek | 2025-11-27 | current | reasoning-llm |  |  |  | Price not published | 2026-09-29 |
| [FLUX.2 [dev]](https://postcutoff.com/m/flux-2-dev/) | Black Forest Labs | 2025-11-25 | current | image-gen |  |  |  | Price not published | 2026-09-29 |
| [FLUX.2 [pro]](https://postcutoff.com/m/flux-2-pro/) | Black Forest Labs | 2025-11-25 | current | image-gen | `flux-2-pro` |  |  | $0.03 per image | 2026-09-29 |
| [Claude Opus 4.5](https://postcutoff.com/m/claude-opus-4-5/) | Anthropic | 2025-11-24 | legacy | reasoning-llm | `claude-opus-4-5-20251101` | 2025-05 | 863 | $5 in, $25 out per 1M tokens | 2026-09-29 |
| [Nano Banana Pro (Gemini 3 Pro Image)](https://postcutoff.com/m/gemini-3-pro-image/) | Google DeepMind | 2025-11-20 | current | image-gen | `gemini-3-pro-image` |  |  | $2 in, $12 out per 1M tokens | 2026-09-29 |
| [Nari Labs Dia2 (1B / 2B)](https://postcutoff.com/m/dia2/) | Nari Labs | 2025-11-19 | current | audio/speech | `nari-labs/Dia2-2B` |  |  | Price not published | 2026-09-29 |
| [π0.6 / π*0.6](https://postcutoff.com/m/pi-0-6/) | Physical Intelligence | 2025-11-17 | legacy | robotics |  |  |  | Price not published |  |
| [Scribe v2 Realtime](https://postcutoff.com/m/elevenlabs-scribe-v2-realtime/) | ElevenLabs | 2025-11-11 | current | audio/speech | `scribe_v2_realtime` |  |  | $0.39 per hour | 2026-09-29 |
| [Omnilingual ASR](https://postcutoff.com/m/omnilingual-asr/) | Meta | 2025-11-10 | current | audio/speech | `omniASR_LLM_7B_v2` |  |  | Price not published | 2026-09-29 |
| [StepFun Step-Audio-EditX](https://postcutoff.com/m/step-audio-editx/) | StepFun | 2025-11-06 | current | audio/speech | `stepfun-ai/Step-Audio-EditX` |  |  | Price not published | 2026-09-29 |
| [Kimi K2 Thinking](https://postcutoff.com/m/kimi-k2-thinking/) | Moonshot AI | 2025-11 | retired | reasoning-llm | `kimi-k2-thinking / kimi-k2-thinking-turbo` |  |  | Price not published | 2026-09-29 |
| [Amazon Nova Premier](https://postcutoff.com/m/nova-premier/) | Amazon | 2025-10-31 | retired | multimodal | `amazon.nova-premier-v1:0` | 2024-10 | 893 | $2.50 in, $12.50 out per 1M tokens | 2026-09-29 |
| [Lyria 2](https://postcutoff.com/m/lyria-2/) | Google DeepMind | 2025-10-27 | legacy | music | `lyria-002` |  |  | $0.06 per clip | 2026-09-29 |
| [Claude Haiku 4.5](https://postcutoff.com/m/claude-haiku-4-5/) | Anthropic | 2025-10-15 | current | reasoning-llm | `claude-haiku-4-5-20251001` | 2025-02 | 874 | $1 in, $5 out per 1M tokens | 2026-09-29 |
| [Veo 3.1](https://postcutoff.com/m/veo-3-1/) | Google DeepMind | 2025-10-15 | preview | video-gen | `veo-3.1-generate-preview` |  |  | $0.40 per second | 2026-09-29 |
| [Chirp 3 Transcription (Google Cloud Speech-to-Text)](https://postcutoff.com/m/chirp-3/) | Google | 2025-10-13 | current | audio/speech | `chirp_3` |  |  | $0.016 per minute | 2026-09-29 |
| [Cosmos Predict 2.5 / Transfer 2.5](https://postcutoff.com/m/cosmos-predict-2-5/) | NVIDIA | 2025-10-06 | legacy | world-model | `nvidia/Cosmos-Predict2.5-2B` |  |  | Price not published | 2026-09-29 |
| [Sora 2](https://postcutoff.com/m/sora-2/) | OpenAI | 2025-10-06 | retired | video-gen | `sora-2` |  |  | $0.10 per second | 2026-09-29 |
| [Deepgram Flux (conversational STT, English + Multilingual)](https://postcutoff.com/m/deepgram-flux/) | Deepgram | 2025-10-02 | current | audio/speech | `flux-general-en` |  |  | $0.0065 per minute | 2026-09-29 |
| [Nano Banana (Gemini 2.5 Flash Image)](https://postcutoff.com/m/gemini-2-5-flash-image/) | Google DeepMind | 2025-10-02 | deprecated | image-gen | `gemini-2.5-flash-image` |  |  | $0.30 in per 1M tokens; $0.039 per image | 2026-09-29 |
| [Neuphonic NeuTTS Air / NeuTTS Nano](https://postcutoff.com/m/neutts/) | Neuphonic | 2025-10-02 | current | audio/speech | `neuphonic/neutts-nano-german` |  |  | Price not published |  |
| [Hume Octave 2 (TTS)](https://postcutoff.com/m/hume-octave-2/) | Hume AI | 2025-10-01 | current | audio/speech | `version: 2` |  |  | $0.15 per 1K characters | 2026-09-29 |
| [Claude Sonnet 4.5](https://postcutoff.com/m/claude-sonnet-4-5/) | Anthropic | 2025-09-29 | deprecated | reasoning-llm | `claude-sonnet-4-5-20250929` | 2025-01 | 881 | $3 in, $15 out per 1M tokens | 2026-10-02 |
| [Gemini Robotics-ER 1.5 / 1.6](https://postcutoff.com/m/gemini-robotics-er-1/) | Google DeepMind | 2025-09-25 | retired | robotics | `gemini-robotics-er-1.6-preview` | 2025-01 | 881 | Price not published | 2026-09-29 |
| [Gemini 2.5 Flash Native Audio (Live, preview)](https://postcutoff.com/m/gemini-2-5-flash-native-audio/) | Google DeepMind | 2025-09-23 | legacy | audio/speech | `gemini-2.5-flash-native-audio-preview-12-2025` |  |  | $0.50 in, $2 out per 1M tokens | 2026-09-29 |
| [IndexTTS-2 / IndexTTS-2.5 (bilibili)](https://postcutoff.com/m/indextts-2/) | bilibili (Index Team) | 2025-09-08 | current | audio/speech | `IndexTeam/IndexTTS-2` |  |  | Price not published | 2026-09-29 |
| [Eleven Sound Effects v2](https://postcutoff.com/m/elevenlabs-sound-effects-v2/) | ElevenLabs | 2025-09 | current | audio/speech | `eleven_text_to_sound_v2` |  |  | $0.12 per minute | 2026-09-29 |
| [RDT2 (and RDT-1B)](https://postcutoff.com/m/rdt2/) | Tsinghua University (TSAIL, thu-ml) | 2025-09 | current | robotics | `robotics-diffusion-transformer/RDT2-VQ` |  |  | Price not published | 2026-09-29 |
| [Agility Digit whole-body control foundation model ("motor cortex")](https://postcutoff.com/m/agility-digit-motor-cortex/) | Agility Robotics | 2025-08-28 | current | robotics |  |  |  | Price not published |  |
| [GPT-Realtime and GPT-Realtime mini](https://postcutoff.com/m/gpt-realtime/) | OpenAI | 2025-08-28 | deprecated | audio/speech | `gpt-realtime` | 2023-10 | 930 | $4 text in, $16 text out per 1M tokens | 2026-09-29 |
| [VibeVoice (ASR, ASR-Streaming, ASR-BitNet, Realtime-0.5B TTS)](https://postcutoff.com/m/vibevoice/) | Microsoft | 2025-08-25 | current | audio/speech | `microsoft/VibeVoice-ASR` |  |  | Price not published | 2026-09-29 |
| [Atlas Large Behavior Model (Boston Dynamics + TRI LBM)](https://postcutoff.com/m/atlas-large-behavior-model/) | Boston Dynamics | 2025-08-20 | current | robotics |  |  |  | Price not published |  |
| [NVIDIA Parakeet / Canary / Nemotron Speech ASR (open)](https://postcutoff.com/m/nvidia-parakeet-canary/) | NVIDIA | 2025-08-14 | current | audio/speech | `nvidia/parakeet-tdt-0.6b-v3` |  |  | Price not published | 2026-09-29 |
| [Claude Opus 4.1](https://postcutoff.com/m/claude-opus-4-1/) | Anthropic | 2025-08-05 | retired | reasoning-llm | `claude-opus-4-1-20250805` |  |  | $15 in, $75 out per 1M tokens | 2026-09-29 |
| [gpt-oss-120b](https://postcutoff.com/m/gpt-oss-120b/) | OpenAI | 2025-08-05 | current | reasoning-llm | `gpt-oss-120b` | 2024-06 | 904 | Price not published | 2026-09-29 |
| [gpt-oss-20b](https://postcutoff.com/m/gpt-oss-20b/) | OpenAI | 2025-08-05 | current | reasoning-llm | `gpt-oss-20b` | 2024-06 | 904 | Price not published | 2026-09-29 |
| [Genie 3](https://postcutoff.com/m/genie-3/) | Google DeepMind | 2025-08 | preview | world-model |  |  |  | Price not published |  |
| [Codestral 25.08](https://postcutoff.com/m/codestral-2508/) | Mistral AI | 2025-07-30 | current | code | `codestral-2508` |  |  | $0.30 in, $0.90 out per 1M tokens | 2026-09-29 |
| [Gemini 2.5 Flash-Lite](https://postcutoff.com/m/gemini-2-5-flash-lite/) | Google DeepMind | 2025-07-22 | legacy | llm | `gemini-2.5-flash-lite` |  |  | $0.10 in, $0.40 out per 1M tokens | 2026-09-29 |
| [Kyutai TTS 1.6B / Kyutai STT + Unmute](https://postcutoff.com/m/kyutai-tts-stt/) | Kyutai | 2025-07-03 | current | audio/speech | `kyutai/tts-1.6b-en_fr` |  |  | Price not published | 2026-09-29 |
| [Voxtral Small](https://postcutoff.com/m/voxtral-small/) | Mistral AI | 2025-07 | current | multimodal | `voxtral-small-2507` |  |  | Price not published | 2026-09-29 |
| [Imagen 4](https://postcutoff.com/m/imagen-4/) | Google DeepMind | 2025-06-24 | retired | image-gen | `imagen-4.0-generate-001` |  |  | Price not published | 2026-09-29 |
| [Gemini 2.5 Flash](https://postcutoff.com/m/gemini-2-5-flash/) | Google DeepMind | 2025-06-17 | legacy | reasoning-llm | `gemini-2.5-flash` | 2025-01 | 881 | $0.30 in, $2.50 out per 1M tokens | 2026-09-29 |
| [Gemini 2.5 Pro](https://postcutoff.com/m/gemini-2-5-pro/) | Google DeepMind | 2025-06-17 | legacy | reasoning-llm | `gemini-2.5-pro` | 2025-01 | 881 | $1.25 in, $10 out per 1M tokens | 2026-09-29 |
| [1X Redwood AI](https://postcutoff.com/m/1x-redwood/) | 1X Technologies | 2025-06-10 | current | robotics |  |  |  | Price not published | 2026-09-29 |
| [Eleven v3](https://postcutoff.com/m/elevenlabs-v3/) | ElevenLabs | 2025-06-03 | current | audio/speech | `eleven_v3` |  |  | $0.08 per 1K characters | 2026-09-29 |
| [SmolVLA (450M)](https://postcutoff.com/m/smolvla/) | Hugging Face | 2025-06-03 | current | robotics | `lerobot/smolvla_base` |  |  | Price not published | 2026-09-29 |
| [FLUX.1 Kontext [pro] / [max]](https://postcutoff.com/m/flux-1-kontext-pro/) | Black Forest Labs | 2025-05-29 | legacy | image-gen | `flux-kontext-pro` |  |  | $0.04 per image | 2026-09-29 |
| [Hume EVI 3 / EVI 4 mini (speech-to-speech)](https://postcutoff.com/m/hume-evi/) | Hume AI | 2025-05-29 | current | audio/speech | `EVI version 3 or 4-mini (set in EVI config)` |  |  | $0.06 per minute | 2026-09-29 |
| [Resemble AI Chatterbox (Turbo / Nano / Multilingual V3)](https://postcutoff.com/m/chatterbox/) | Resemble AI | 2025-05-28 | current | audio/speech | `ResembleAI/chatterbox` |  |  | Price not published | 2026-09-29 |
| [Claude Sonnet 4](https://postcutoff.com/m/claude-sonnet-4/) | Anthropic | 2025-05-22 | retired | reasoning-llm | `claude-sonnet-4-20250514` |  |  | $3 in, $15 out per 1M tokens | 2026-09-29 |
| [Gemini 2.5 Flash TTS / Pro TTS](https://postcutoff.com/m/gemini-2-5-tts/) | Google DeepMind | 2025-05-20 | legacy | audio/speech | `gemini-2.5-flash-preview-tts` |  |  | $0.50 in, $10 out per 1M tokens | 2026-09-29 |
| [π0.5](https://postcutoff.com/m/pi-0-5/) | Physical Intelligence | 2025-04-22 | current | robotics | `gs://openpi-assets/checkpoints/pi05_base` |  |  | Price not published | 2026-09-29 |
| [o3](https://postcutoff.com/m/o3/) | OpenAI | 2025-04-16 | deprecated | reasoning-llm | `o3` | 2024-06 | 904 | $2 in, $8 out per 1M tokens | 2026-09-29 |
| [Deepgram Aura-2](https://postcutoff.com/m/deepgram-aura-2/) | Deepgram | 2025-04-15 | current | audio/speech | `aura-2-thalia-en` |  |  | $0.03 per 1K characters | 2026-09-29 |
| [GPT-4.1](https://postcutoff.com/m/gpt-4-1/) | OpenAI | 2025-04-14 | legacy | llm | `gpt-4.1` | 2024-06 | 904 | $2 in, $8 out per 1M tokens | 2026-09-29 |
| [Llama 4 Maverick (17B-128E)](https://postcutoff.com/m/llama-4-maverick/) | Meta | 2025-04-05 | legacy | multimodal | `meta.llama4-maverick-17b-instruct-v1:0` | 2024-08 | 900 | Price not published | 2026-09-29 |
| [Llama 4 Scout (17B-16E)](https://postcutoff.com/m/llama-4-scout/) | Meta | 2025-04-05 | legacy | multimodal | `meta.llama4-scout-17b-instruct-v1:0` | 2024-08 | 900 | Price not published | 2026-09-29 |
| [Chirp 3 HD voices (Google Cloud Text-to-Speech)](https://postcutoff.com/m/chirp-3-hd/) | Google | 2025-04-02 | current | audio/speech | `<locale>-Chirp3-HD-<Voice> (e.g. en-US-Chirp3-HD-Charon)` |  |  | $30 per 1M characters | 2026-09-29 |
| [Cohere Embed v4](https://postcutoff.com/m/cohere-embed-v4/) | Cohere | 2025-04 | current | embedding | `embed-v4.0` |  |  | Price not published | 2026-09-29 |
| [GPT-4o mini TTS](https://postcutoff.com/m/gpt-4o-mini-tts/) | OpenAI | 2025-03-20 | current | audio/speech | `gpt-4o-mini-tts` |  |  | $0.60 text in, $12 audio out per 1M tokens | 2026-09-29 |
| [GPT-4o Transcribe / Mini Transcribe / Transcribe Diarize](https://postcutoff.com/m/gpt-4o-transcribe/) | OpenAI | 2025-03-20 | deprecated | audio/speech | `gpt-4o-transcribe` | 2024-06 | 904 | $2.50 in, $10 out per 1M tokens | 2026-09-29 |
| [Isaac GR00T N1 / N1.5 / N1.6](https://postcutoff.com/m/gr00t-n1/) | NVIDIA | 2025-03-18 | legacy | robotics | `nvidia/GR00T-N1-2B` |  |  | Price not published | 2026-09-29 |
| [Sesame CSM-1B (Conversational Speech Model)](https://postcutoff.com/m/sesame-csm-1b/) | Sesame | 2025-03-13 | current | audio/speech | `sesame/csm-1b` |  |  | Price not published | 2026-09-29 |
| [AgiBot GO-1 (Genie Operator-1)](https://postcutoff.com/m/agibot-go-1/) | AgiBot | 2025-03-10 | legacy | robotics | `agibot-world/GO-1` |  |  | Price not published | 2026-09-29 |
| [Canopy Labs Orpheus TTS (3B)](https://postcutoff.com/m/orpheus-tts/) | Canopy Labs | 2025-03 | current | audio/speech | `canopylabs/orpheus-tts-0.1-finetune-prod` |  |  | Price not published | 2026-09-29 |
| [Command A (03-2025) and variants](https://postcutoff.com/m/command-a/) | Cohere | 2025-03 | legacy | llm | `command-a-03-2025` |  |  | $2.50 in, $10 out per 1M tokens | 2026-09-29 |
| [Scribe v1](https://postcutoff.com/m/elevenlabs-scribe-v1/) | ElevenLabs | 2025-02-26 | deprecated | audio/speech | `scribe_v1` |  |  | Price not published | 2026-09-29 |
| [Helix (Figure, v1)](https://postcutoff.com/m/figure-helix/) | Figure AI | 2025-02-20 | legacy | robotics |  |  |  | Price not published |  |
| [Deepgram Nova-3 (incl. Medical / Pharma)](https://postcutoff.com/m/deepgram-nova-3/) | Deepgram | 2025-02-12 | current | audio/speech | `nova-3` |  |  | $0.0048 per minute | 2026-09-29 |
| [Kokoro-82M](https://postcutoff.com/m/kokoro-82m/) | hexgrad | 2025-01-27 | current | audio/speech | `hexgrad/Kokoro-82M` |  |  | $0.65 per 1M characters | 2026-09-29 |
| [π0-FAST](https://postcutoff.com/m/pi-0-fast/) | Physical Intelligence | 2025-01-16 | legacy | robotics | `gs://openpi-assets/checkpoints/pi0_fast_base` |  |  | Price not published | 2026-09-29 |
| [Eleven Flash v2.5 / Flash v2](https://postcutoff.com/m/elevenlabs-flash-v2-5/) | ElevenLabs | 2024-12-18 | current | audio/speech | `eleven_flash_v2_5` |  |  | $0.04 per 1K characters | 2026-09-29 |
| [Phi-4 (14B)](https://postcutoff.com/m/phi-4/) | Microsoft | 2024-12-12 | legacy | llm | `Phi-4` |  |  | $0.07 in, $0.14 out per 1M tokens | 2026-09-29 |
| [π0 (pi-zero)](https://postcutoff.com/m/pi-0/) | Physical Intelligence | 2024-10-31 | legacy | robotics | `gs://openpi-assets/checkpoints/pi0_base` |  |  | Price not published | 2026-09-29 |
| [Stable Diffusion 3.5 Large](https://postcutoff.com/m/stable-diffusion-3-5-large/) | Stability AI | 2024-10-22 | current | image-gen | `sd3.5-large` |  |  | Price not published |  |
| [Kyutai Moshi / Hibiki-Zero (full-duplex speech models)](https://postcutoff.com/m/kyutai-moshi/) | Kyutai | 2024-09-17 | current | audio/speech | `kyutai/moshiko-pytorch-bf16` |  |  | Price not published | 2026-09-29 |
| [OpenVLA (7B) and OpenVLA-OFT](https://postcutoff.com/m/openvla/) | Stanford / UC Berkeley / Toyota Research Institute | 2024-06-13 | legacy | robotics | `openvla/openvla-7b` |  |  | Price not published | 2026-09-29 |
| [Octo (Octo-Small / Octo-Base 1.5)](https://postcutoff.com/m/octo/) | UC Berkeley (RAIL) / Stanford / CMU / Google DeepMind | 2024-05-20 | legacy | robotics | `rail-berkeley/octo-base-1.5` |  |  | Price not published | 2026-09-29 |
| [GPT-4o](https://postcutoff.com/m/gpt-4o/) | OpenAI | 2024-05-13 | legacy | multimodal | `gpt-4o` | 2023-10 | 930 | $2.50 in, $10 out per 1M tokens | 2026-09-29 |
| [text-embedding-3-large](https://postcutoff.com/m/text-embedding-3-large/) | OpenAI | 2024-01-25 | current | embedding | `text-embedding-3-large` |  |  | $0.13 in per 1M tokens | 2026-09-29 |
| [text-embedding-3-small](https://postcutoff.com/m/text-embedding-3-small/) | OpenAI | 2024-01-25 | current | embedding | `text-embedding-3-small` |  |  | $0.02 in per 1M tokens | 2026-09-29 |
| [Tesla Optimus AI (end-to-end robot neural network)](https://postcutoff.com/m/tesla-optimus-ai/) | Tesla | 2024 | preview | robotics |  |  |  | Price not published |  |
| [TTS-1 / TTS-1 HD](https://postcutoff.com/m/tts-1/) | OpenAI | 2023-11-06 | legacy | audio/speech | `tts-1` |  |  | $15 per 1M characters | 2026-09-29 |
| [Whisper large-v3 / large-v3-turbo (open weights)](https://postcutoff.com/m/whisper-large-v3/) | OpenAI | 2023-11-06 | legacy | audio/speech | `openai/whisper-large-v3` |  |  | Price not published | 2026-09-29 |
| [Eleven Multilingual v2](https://postcutoff.com/m/elevenlabs-multilingual-v2/) | ElevenLabs | 2023-08-22 | current | audio/speech | `eleven_multilingual_v2` |  |  | $0.08 per 1K characters | 2026-09-29 |
| [Whisper (whisper-1 API)](https://postcutoff.com/m/whisper-1/) | OpenAI | 2023-03-01 | deprecated | audio/speech | `whisper-1` |  |  | $0.006 per minute | 2026-09-29 |
| [Eleven Multilingual STS v2 (Voice Changer)](https://postcutoff.com/m/elevenlabs-voice-changer-sts-v2/) | ElevenLabs |  | current | audio/speech | `eleven_multilingual_sts_v2` |  |  | $0.12 per minute | 2026-09-29 |
| [Eleven Turbo v2.5 / Turbo v2](https://postcutoff.com/m/elevenlabs-turbo-v2-5/) | ElevenLabs |  | deprecated | audio/speech | `eleven_turbo_v2_5` |  |  | $0.04 per 1K characters | 2026-09-29 |
| [Eleven Voice Design v3 (Text to Voice)](https://postcutoff.com/m/elevenlabs-voice-design-v3/) | ElevenLabs |  | current | audio/speech | `eleven_ttv_v3` |  |  | Price not published | 2026-09-29 |
| [Lyria RealTime](https://postcutoff.com/m/lyria-realtime/) | Google DeepMind |  | preview | music | `models/lyria-realtime-exp` |  |  | Price not published | 2026-09-29 |