← All providers
Together AI
36 models · routes through the @ai-sdk/togetherai adapter
Required environment variables
- TOGETHER_API_KEY
Models
| Model | Context | Input | Output | Capabilities |
|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Pro-0813 | 1049k | $1.32 / 1M | $3.96 / 1M | tools, reasoning, open-weights |
| deepseek-ai/DeepSeek-V4-Flash-0731 | 1000k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| moonshotai/Kimi-K3 | 1049k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| thinkingmachines/Inkling | 524k | $1.00 / 1M | $4.05 / 1M | tools, reasoning, open-weights, vision |
| zai-org/GLM-5.2 | 512k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| moonshotai/Kimi-K2.7-Code | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights |
| MiniMaxAI/MiniMax-M3 | 524k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights, vision |
| nvidia/nemotron-3-ultra-550b-a55b | 512k | $0.60 / 1M | $3.60 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.7-Max | 1000k | $1.25 / 1M | $3.75 / 1M | tools |
| Qwen/Qwen3.6-Plus | 1000k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, open-weights |
| deepseek-ai/DeepSeek-V4-Pro | 512k | $1.74 / 1M | $3.48 / 1M | tools, reasoning, open-weights |
| moonshotai/Kimi-K2.6 | 262k | $1.20 / 1M | $4.50 / 1M | tools, reasoning, open-weights, vision |
| google/gemma-4-31B-it | 262k | $0.39 / 1M | $0.97 / 1M | tools, reasoning, open-weights, vision |
| pearl-ai/gemma-4-31b-it | 32k | $0.28 / 1M | $0.86 / 1M | reasoning |
| zai-org/GLM-5.1deprecated | 203k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| MiniMaxAI/MiniMax-M2.7 | 203k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.5-9B | 262k | $0.17 / 1M | $0.25 / 1M | tools, reasoning, open-weights, vision |
| LiquidAI/LFM2-24B-A2B | 33k | $0.03 / 1M | $0.12 / 1M | open-weights |
| Qwen/Qwen3.5-397B-A17Bdeprecated | 262k | $0.60 / 1M | $3.60 / 1M | tools, reasoning, open-weights, vision |
| MiniMaxAI/MiniMax-M2.5deprecated | 205k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| zai-org/GLM-5deprecated | 203k | $1.00 / 1M | $3.20 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-Coder-Next-FP8deprecated | 262k | $0.50 / 1M | $1.20 / 1M | tools, open-weights |
| moonshotai/Kimi-K2.5deprecated | 262k | $0.50 / 1M | $2.80 / 1M | tools, reasoning, open-weights, vision |
| essentialai/Rnj-1-Instructdeprecated | 33k | $0.15 / 1M | $0.15 / 1M | tools, open-weights |
| deepcogito/cogito-v2-1-671b | 164k | $1.25 / 1M | $1.25 / 1M | reasoning |
| deepseek-ai/DeepSeek-V3-1deprecated | 131k | $0.60 / 1M | $1.70 / 1M | tools, reasoning, open-weights |
| openai/gpt-oss-120b | 131k | $0.15 / 1M | $0.60 / 1M | tools, reasoning, open-weights |
| openai/gpt-oss-20b | 131k | $0.05 / 1M | $0.20 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-235B-A22B-Instruct-2507-tputdeprecated | 262k | $0.20 / 1M | $0.60 / 1M | tools, open-weights |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8deprecated | 262k | $2.00 / 1M | $2.00 / 1M | tools, open-weights |
| google/gemma-3n-E4B-it | 33k | $0.06 / 1M | $0.12 / 1M | open-weights |
| deepseek-ai/DeepSeek-R1deprecated | 164k | $3.00 / 1M | $7.00 / 1M | reasoning, open-weights |
| deepseek-ai/DeepSeek-V3deprecated | 131k | $1.25 / 1M | $1.25 / 1M | tools, open-weights |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | 131k | $1.04 / 1M | $1.04 / 1M | tools, open-weights |
| Qwen/Qwen2.5-7B-Instruct-Turbo | 33k | $0.30 / 1M | $0.30 / 1M | tools, open-weights |
| meta-llama/Meta-Llama-3-8B-Instruct-Lite | 8k | $0.14 / 1M | $0.14 / 1M | open-weights |
Sourced from models.dev. Pricing reflects the catalog at the time this page was rendered.