This website uses cookies to anonymously analyze website traffic using Google Analytics.
AcceptDecline

Model Library

Build with leading open-source models

Explore top-performing models across chat, vision, code, and audio - optimized for production deployment

Start building nowRequest dedicated endpoint

Featured

models

Chat

DeepSeek-R1-0528

Upgraded DeepSeek-R1 with better reasoning, function calling, and coding, using 23K-token thinking to score 87.5% on AIME.

TRY THIS MODEL

Chat

Kimi K2 Instruct-0905

Upgraded state-of-the-art mixture-of-experts agentic intelligence model with 1T parameters, 256K context, and native tool use

TRY THIS MODEL

New

Chat

Qwen3 235B A22B FP8 Throughput

Hybrid instruct + reasoning model (232Bx22B MoE) optimized for high-throughput, cost-efficient inference and distillation.

TRY THIS MODEL

Chat

Qwen3 235B A22B Instruct 2507 FP8

235B MoE model with 22B activation featuring enhanced instruction following, reasoning, and 262K context for cost-efficient high-throughput inference.

TRY THIS MODEL

Chat

Llama 4 Maverick

SOTA 128-expert MoE powerhouse for multilingual image/text understanding, creative writing, and enterprise-scale applications.

TRY THIS MODEL

Chat

Llama 4 Scout

SOTA 109B model with 17B active params & large context, excelling at multi-document analysis, codebase reasoning, and personalized tasks.

TRY THIS MODEL

Chat

Gemma 3 27B

Lightweight model with vision-language input, multilingual support, visual reasoning, and top-tier performance per size.

TRY THIS MODEL

Chat

DeepSeek-V3-0324

DeepSeek's latest open Mixture-of-Experts model challenging top AI models at much lower cost.

TRY THIS MODEL

Chat

DeepSeek-V3.1

671B parameters (37B activated), 128K context, hybrid thinking/non-thinking modes, advanced tool calling, agent capabilities

TRY THIS MODEL

New

Chat

DeepSeek-R1-0528 Throughput

Throughput DeepSeek-R1 is a state of the art reasoning model trained with reinforcement learning. It delivers strong performance on math, code, and logic tasks – comparable to OpenAI-o1. It is especially good at tasks like code review, document analysis, planning, information extraction, and coding.

TRY THIS MODEL

Chat

Qwen QwQ-32B

Qwen series reasoning model excelling in complex tasks, outperforming conventional instruction-tuned models on hard problems.

TRY THIS MODEL

All

Chat

DeepSeek-V3-0324

DeepSeek's latest open Mixture-of-Experts model challenging top AI models at much lower cost.

TRY THIS MODEL

DeepSeek

Chat

gpt-oss-120B

120B parameters, 128K context, reasoning with chain-of-thought, MoE architecture, Apache 2.0 license

TRY THIS MODEL

New
OpenAI

Chat

DeepSeek-V3.1

671B parameters (37B activated), 128K context, hybrid thinking/non-thinking modes, advanced tool calling, agent capabilities

TRY THIS MODEL

New
DeepSeek

Chat

Kimi K2 Instruct-0905

Upgraded state-of-the-art mixture-of-experts agentic intelligence model with 1T parameters, 256K context, and native tool use

TRY THIS MODEL

New
Moonshot AI

Chat

Qwen3 235B A22B Instruct 2507 FP8

235B MoE model with 22B activation featuring enhanced instruction following, reasoning, and 262K context for cost-efficient high-throughput inference.

TRY THIS MODEL

Qwen

Chat

GLM-4.5-Air

106B‑parameter efficient MoE model, 128K‑token context, hybrid reasoning modes, optimized for superior efficiency while maintaining competitive performance.

TRY THIS MODEL

New
ZAI

Chat

Qwen3-Next-80B-A3B-Instruct

80B parameters (3B activated), instruction-tuned MoE, 10x faster inference, hybrid attention mechanisms

TRY THIS MODEL

New
Qwen

Chat

Qwen3-Next-80B-A3B-Thinking

80B parameters (3B activated), reasoning-optimized MoE, 10x faster inference, advanced thinking capabilities

TRY THIS MODEL

Qwen

Transcribe

Whisper Large v3

High-performance speech-to-text model delivering transcription 15x faster than OpenAI with support for 1GB+ files, 50+ languages, and production-ready infrastructure.

TRY THIS MODEL

OpenAI

Chat

Kimi K2 Instruct

State-of-the-art mixture-of-experts agentic intelligence model with 1 T parameters, 128K context, and native tool use

TRY THIS MODEL

Moonshot AI

Chat

Cogito v2 preview - 671B MoE

671B mixture-of-experts model matching Deepseek R1 performance, 60% shorter reasoning chains, approaching o3 and Claude 4 capabilities

TRY THIS MODEL

New
Deep Cogito

Chat

DeepSeek-R1-0528

Upgraded DeepSeek-R1 with better reasoning, function calling, and coding, using 23K-token thinking to score 87.5% on AIME.

TRY THIS MODEL

DeepSeek

Chat

Llama 4 Maverick

SOTA 128-expert MoE powerhouse for multilingual image/text understanding, creative writing, and enterprise-scale applications.

TRY THIS MODEL

Meta

Embeddings

BGE-Base-EN v1.5

BAAI general embedding - base, english - model v1.5. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.

TRY THIS MODEL

BAAI

Embeddings

GTE ModernBERT base

Text embedding and rerank models built on modernBERT, excelling in MTEB, LoCO, and COIR retrieval benchmarks.

TRY THIS MODEL

Alibaba-NLP

Code

Qwen3-Coder 480B A35B Instruct

480B-parameter MoE coding model with 35B active, 256K context, and agentic performance rivaling Claude Sonnet on complex development tasks.

TRY THIS MODEL

Qwen

Chat

Qwen3 235B A22B Thinking 2507 FP8

235B-parameter MoE thinking model, 256K context, 22B activated experts, state-of-the-art reasoning performance among open-source models.

TRY THIS MODEL

Qwen

Audio

Cartesia Sonic-2

Low-latency, ultra-realistic voice model, served in partnership with Cartesia.

TRY THIS MODEL

Cartesia

Chat

Gemma 3 27B

Lightweight model with vision-language input, multilingual support, visual reasoning, and top-tier performance per size.

TRY THIS MODEL

Google

Image

FLUX.1 Kontext [dev]

In-context image generation and editing model using both text and image inputs.

TRY THIS MODEL

Black Forest Labs

No search results.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Run any model on the fastest endpoints

Use our API to deploy any open-source model on the fastest inference stack available with optimal cost efficiency.

Scale into a dedicated deployment anytime with a custom number of instances to get optimal throughput.

Start buildingRequest dedicated endpoint
Curl
Python
Typescript

RUN INFERENCE

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
	"model": "meta-llama/Llama-Vision-Free",
	"messages": [{"role": "user", "content": "What are some fun things to do in New York?"}]
  }'

RUN INFERENCE

from together import Together

client = Together()

response = client.chat.completions.create(
    model="meta-llama/Llama-Vision-Free",
    messages=[{"role": "user", "content": "What are some fun things to do in New York?"}],
)

print(response.choices[0].message.content)

RUN INFERENCE

import Together from "together-ai";

const together = new Together({ apiKey: process.env.TOGETHER_API_KEY });

const response = await together.chat.completions.create({
    messages: [{"role": "user", "content": "What are some fun things to do in New York?"}],
    model: "meta-llama/Llama-Vision-Free",
});

console.log(response.choices[0].message.content)

Subscribe to newsletter

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.