Models

Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to 25 MB), text input is limited to 128 tokens, and vectors are 1,024 dimensions by default with 384 and 256 selectable via the dimensions parameter.

Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. It accepts up to 8,192 tokens per input and returns fixed 1,536-dimension vectors; the dimensions parameter is not supported.

Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions by default, with 512 and 256 also selectable via the dimensions parameter.

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams 44.1 kHz mono PCM audio, with support for 39 languages and up to 5,000 characters per request.

HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams 44.1 kHz mono PCM audio, with support for 39 languages and up to 5,000 characters per request.

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited for investigating codebases, fixing bugs, implementing features, and writing tests.

Mammoth 1 is a 27B decision model from Base Labs, Baseten's research team, built on Qwen3.5-27B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatible and suits classification, routing, and scoring where you need a scored answer instead of prose. Its smaller sibling is Elephant 1.

Elephant 1 is a 9B decision model from Base Labs, Baseten's research team, built on Qwen3.5-9B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatible and suits routing, classification, and scoring where you need a scored answer instead of prose. Its larger sibling is Mammoth 1.

Drex Max is the largest decision model from Nace.AI, the successor to Drex v2.0. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatible and suits routing, classification, and policy checks that need a scored answer instead of prose.

Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 2048-dim vectors that can be truncated, and shares the text embedding space of Nemotron 3 Embed 1B.

Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 4096-dim vectors that can be truncated, and shares the text embedding space of Nemotron 3 Embed 8B.

Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in the input to control delivery. It streams audio with low time-to-first-audio and suits voice agents, narration, and multilingual assistants.

Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited for high-accuracy multilingual transcription of meetings, interviews, media, and support calls.

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms. It is small enough to self-deploy in resource-constrained environments, and fits meeting notes, call analytics, and voice-agent pipelines where cost matters.

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.