Providers/Together AI

Together AI

Inference provider · together.ai

Together AI models via API.

Models

104

Endpoints

5

Regions

1

Avg input

$0.72

Auth

Bearer token

SDKs

2

Endpoints

POST/v1/chat/completionsCompletionsStream

POST/v1/embeddingsEmbeddings-

POST/v1/messagesMessagesStream

POST/v1/moderationsModerations-

POST/v1/responsesResponsesStream

Models · 104

ModelContextInputOutputCapabilities

DeepSeek-V4.1-FlashOpen1.0M$0.30$1.20ToolsJSON GLM-5.3-FlashOpen1.0M$0.15$0.50ReasoningVisionTools Qwen3.8-FlashOpen1M$0.15$0.47 GLM-5.3Open1.0M$1.40$4.40ReasoningToolsJSON DeepSeek-V4-Pro-0813Open1.0M$1.32$3.96ToolsJSON Qwen3.8-2.4T-A95BOpen1.0M$2.00$6.00 Muse-Glimmer-30BOpen131K$0.35$1.50 DeepSeek-V4-Flash-0731Open1.0M$0.14$0.28ToolsJSON Inkling-SmallOpen524K$0.50$1.20 InklingOpen524K$1.00$4.05ToolsJSON Kimi-K3Open1.0M$3.00$15.00ReasoningVisionTools GLM-5.2Open1.0M$1.40$4.40ReasoningToolsJSON Kimi-K2.7-CodeOpen262K$0.95$4.00VisionToolsJSON nemotron-3-ultra-550b-a55bOpen512K$0.60$3.60ReasoningToolsJSON Qwen3.7-PlusOpen1M$0.32$1.28 MiniMax-M3Open524K$0.30$1.20ReasoningVisionTools Qwen3.7-MaxOpen1M$2.50$7.50 DeepSeek-V4-ProOpen512K$1.74$3.48ReasoningToolsJSON Kimi-K2.6Open262K$1.20$4.50 GLM-5.1Open203K$1.40$4.40 Qwen3.6-PlusOpen1M$0.50$3.00Reasoning gemma-4-31B-itOpen262K$0.39$0.97VisionToolsJSON gemma-4-31b-itOpen262K$0.28$0.86 MiniMax-M2.7Open197K$0.30$1.20 Qwen3.5-9BOpen262K$0.17$0.25ReasoningVisionTools Qwen3.5-397B-A17BOpen262K$0.60$3.60ToolsJSON GLM-5Open203K$1.00$3.20 Kimi-K2.5Open256K$0.50$2.80ReasoningVisionTools GLM-4.7Open200K$0.45$2.00ReasoningTools Qwen3-VL-32B-InstructOpen262K$0.50$1.50 Qwen3-VL-8B-InstructOpen262K$0.18$0.68 GLM-4.6Open200K$0.60$2.20ReasoningTools Qwen3-Next-80B-A3B-InstructOpen262K$0.15$1.50ToolsJSON Qwen3-Next-80B-A3B-ThinkingOpen262K$0.15$1.50ToolsJSON gpt-oss-120bOpen131K$0.15$0.60ReasoningToolsJSON gpt-oss-20bOpen131K$0.05$0.20ToolsJSON Qwen3-235B-A22B-Thinking-2507Open256K$0.65$3.00ToolsJSON DeepSeek-R1-0528Open164K$3.00$7.00 Llama-Guard-4-12BOpen1.0M$0.20$0.20 Llama-4-Scout-17B-16E-InstructOpen0$0.18$0.59ToolsJSON Qwen2.5-VL-72B-InstructOpen0$1.95$8.00 Mistral-Small-24B-Instruct-2501Open33K$0.10$0.30Tools DeepSeek-R1-Distill-Llama-70BOpen0$2.00$2.00 DeepSeek-R1Open128K$3.00$7.00ToolsJSON Qwen2.5-Coder-32B-InstructOpen0$0.80$0.80 Llama-3.2-1B-InstructOpen0$0.06$0.06 Llama-3.2-3B-InstructOpen0$0.06$0.06 Qwen2.5-72B-InstructOpen0$1.20$1.20 gemma-2-27b-itOpen0$0.80$0.80 CodeLlama-34b-InstructOpen0$0.00-Tools DeepSeek-R1-0528-tputOpen128K$0.55$2.19ToolsJSON DeepSeek-R1-Distill-Qwen-1.5BOpen0$0.18$0.18 DeepSeek-R1-Distill-Qwen-14BOpen0$1.60$1.60 DeepSeek-V3Open66K$1.25$1.25ToolsJSON DeepSeek-V3.1Open131K$0.60$1.70ReasoningTools GLM-4.5-Air-FP8131K$0.20$1.10ToolsJSON Kimi-K2-InstructOpen0$1.00$3.00ToolsJSON Kimi-K2-Instruct-0905Open262K$1.00$3.00Tools Kimi-K2.5-fp4Open262K$0.50$2.80 Llama-3-8b-chat-hfOpen0$0.20$0.20 Llama-3.1-405B-InstructOpen0$3.50$3.50 Llama-3.1-Nemotron-70B-Instruct-HFOpen0$0.88$0.88 Llama-3.2-3B-Instruct-TurboOpen0$0.00-ToolsJSON Llama-3.3-70B-Instruct-TurboOpen131K$1.04$1.04ToolsJSON Llama-3.3-70B-Instruct-Turbo-FreeOpen0$0.00$0.00ToolsJSON Llama-4-Maverick-17B-128E-Instruct-FP8Open0$0.27$0.85ToolsJSON Meta-Llama-3-70B-Instruct-TurboOpen0$0.88$0.88 Meta-Llama-3-8B-InstructOpen0$0.20$0.20 Meta-Llama-3.1-405B-Instruct-TurboOpen0$3.50$3.50ToolsJSON Meta-Llama-3.1-70B-Instruct-TurboOpen0$0.88$0.88ToolsJSON Meta-Llama-3.1-8B-Instruct-TurboOpen0$0.18$0.18ToolsJSON Ministral-3-14B-Instruct-2512Open262K$0.20$0.20 Mistral-7B-Instruct-v0.1Open33K$0.20$0.20ToolsJSON Mistral-7B-Instruct-v0.3Open33K$0.20$0.20 Mixtral-8x7B-Instruct-v0.1Open0$0.60$0.60ToolsJSON NVIDIA-Nemotron-Nano-9B-v2Open131K$0.06$0.25 Nous-Hermes-2-Mixtral-8x7B-DPOOpen0$0.60$0.60 QwQ-32BOpen131K$1.20$1.20 Qwen2-1.5B-InstructOpen0$0.02$0.02 Qwen2-72B-InstructOpen0$0.90$0.90 Qwen2-VL-72B-InstructOpen0$1.20$1.20 Qwen2.5-14B-InstructOpen0$0.80$0.80 Qwen2.5-72B-Instruct-TurboOpen131K$1.20$1.20ToolsJSON Qwen2.5-7B-Instruct-TurboOpen33K$0.30$0.30ToolsJSON Qwen3-235B-A22B-Instruct-2507-tputOpen262K$0.20$6.00ToolsJSON Qwen3-235B-A22B-fp8-tputOpen40K$0.20$0.60 Qwen3-Coder-480B-A35B-Instruct-FP8Open262K$2.00$2.00ToolsJSON Qwen3-Coder-Next-FP8Open262K$0.50$1.20 Ternary-Bonsai-27B262K$0.00$0.00 bge-base-en-v1.5512$0.01$0.00Embeddings bge-base-en-v1.5512$0.01$0.00Embeddings deepseek-coder-33b-instructOpen0$0.80$0.80 gemma-3n-E4B-itOpen33K$0.06$0.12 multilingual-e5-large-instruct514$0.02$0.02Embeddings qwen-2-1.5b-instructOpen33K$0.10$0.10 together-ai-21.1b-41b0$0.80$0.80 together-ai-4.1b-8b0$0.20$0.20 together-ai-41.1b-80b0$0.90$0.90 together-ai-8.1b-21b1K$0.30$0.30 together-ai-81.1b-110b0$1.80$1.80 together-ai-embedding-151m-to-350m0$0.02$0.00Embeddings together-ai-embedding-up-to-150m0$0.01$0.00Embeddings together-ai-up-to-4b0$0.10$0.10 trinity-mini0$0.04$0.15

Release timeline

Aug 2026

Qwen3.8-2.4T-A95B

Aug 2026

GLM-5.3

Aug 2026

GLM-5.3-Flash

Aug 2026

Qwen3.8-Flash

Sep 2026

DeepSeek-V4.1-Flash

Details

CategoryInference provider

Websitetogether.ai

AuthBearer token

Regions1

Regions

global

SDKs

pip install together

TypeScriptdocs ↗

npm install together-ai