Together AI models and pricing
We track 16 models on Together AI from 10 labs. The cheapest paid model is Qwen/Qwen3.5-9B, at $0.17 per million input tokens and $0.25 per million output tokens. Input prices range from $0.15 to $3 and output prices from $0.25 to $15 per million tokens. The largest context window is 1M tokens (Kimi K3.1 Pro Highspeed, Muse Spark Open and 4 other models). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on Together AI
- Qwen/Qwen3.5-9B$0.17 / $0.25
- GLM-5.3-Flash$0.15 / $0.50
- NVIDIA Nemotron 3.5 Super VL$0.15 / $0.50
- gpt-oss-120b$0.15 / $0.60
- DeepSeek V4.1 Flash$0.30 / $1.20
Input / output per million tokens, paid models, by combined price.
Newest models on Together AI
- Kimi K3.1 Pro Highspeed23 Oct 2026
- Muse Spark Open15 Oct 2026
- NVIDIA Nemotron 3.5 Super VL15 Oct 2026
- Beam 1.05 Oct 2026
- DeepSeek V4.1 Flash10 Sept 2026
By the lab's release date.
All Together AI models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| Kimi K3.1 Pro Highspeed moonshotai/Kimi-K3.1-Pro | Moonshot AI | $2 | $10 | 1M | models.dev |
| Muse Spark Open meta-models/Muse-Spark-Open-816B-A42B | Meta | $1.25 | $4.25 | 1M | models.dev |
| NVIDIA Nemotron 3.5 Super VL nvidia/NVIDIA-Nemotron-3.5-Super-VL | NVIDIA | $0.15 | $0.50 | 262K | models.dev |
| Beam 1.0 reflection/Beam-1.0-501B-A23B | Reflection | $0.40 | $1.20 | 1M | models.dev |
| DeepSeek V4.1 Flash deepseek-ai/DeepSeek-V4.1-Flash | DeepSeek | $0.30 | $1.20 | 1M | models.dev |
| GLM-5.3-Flash zai-org/GLM-5.3-Flash | Zhipu AI (Z.ai) | $0.15 | $0.50 | 1M | models.dev |
| GLM-5.3 zai-org/GLM-5.3 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro-0813 | DeepSeek | $1.32 | $3.96 | 1M | models.dev |
| Kimi K3 moonshotai/Kimi-K3 | Moonshot AI | $3 | $15 | 1M | models.dev |
| Inkling thinkingmachines/Inkling | Thinkingmachines | $1 | $4.05 | 524K | models.dev |
| GLM-5.2 zai-org/GLM-5.2 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| MiniMax-M3 MiniMaxAI/MiniMax-M3 | MiniMax | $0.30 | $1.20 | 524K | models.dev |
| Qwen3.7 Max Qwen/Qwen3.7-Max | Alibaba (Qwen) | $2.50 | $7.50 | 1M | models.dev |
| Qwen3.6 Plus Qwen/Qwen3.6-Plus | Alibaba (Qwen) | $0.50 | $3 | 1M | models.dev |
| Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B | Alibaba (Qwen) | $0.17 | $0.25 | 262K | models.dev |
| gpt-oss-120b openai/gpt-oss-120b | OpenAI | $0.15 | $0.60 | 131K | models.dev |
Frequently asked questions
How much does Together AI cost per million tokens?
Prices on Together AI depend on the model. Across the 16 models we track, input costs $0.15 to $3 per million tokens and output costs $0.25 to $15 per million tokens. Prices last verified 18 Nov 2026.
What is the cheapest model on Together AI?
Qwen/Qwen3.5-9B from Alibaba (Qwen) is the cheapest paid model we track on Together AI, at $0.17 per million input tokens and $0.25 per million output tokens. Next are GLM-5.3-Flash ($0.15 / $0.50) and NVIDIA Nemotron 3.5 Super VL ($0.15 / $0.50). Prices last verified 18 Nov 2026.
How many models does Together AI offer?
We currently track 16 active models on Together AI from 10 labs, led by Alibaba (Qwen) (3), Zhipu AI (Z.ai) (3), DeepSeek (2) and Moonshot AI (2).
Which model on Together AI has the largest context window?
Kimi K3.1 Pro Highspeed, Muse Spark Open and 4 other models share the largest context window we track on Together AI: 1,048,576 tokens (1M).