Together AI LLM API pricing
Every model Together AI serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models Together AI lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
99
on this provider
Cheapest input
$0.02
per 1M tokens
Cheapest output
$0.02
per 1M tokens
Max context
10.5M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| Qwen2 1 5B Instruct | Alibaba | 33K | $0.02 | $0.02 | together_ai/Qwen/Qwen2-1.5B-Instruct |
| Tev1 4B Experimental | Other | 33K | $0.042 | n/a | together_ai/together/Tev1-4B-experimental |
| Trinity Mini | Other | 128K | $0.045 | $0.15 | together_ai/arcee-ai/trinity-mini |
| gpt-oss-20b | OpenAI | 131K | $0.05 | $0.20 | together_ai/openai/gpt-oss-20b |
| Gemma 3n E4b It | 33K | $0.06 | $0.12 | together_ai/google/gemma-3n-E4B-it | |
| Llama 3.2 1B Instruct | Meta | 131K | $0.06 | $0.06 | together_ai/meta-llama/Llama-3.2-1B-Instruct |
| Llama 3.2 3B Instruct | Meta | 131K | $0.06 | $0.06 | together_ai/meta-llama/Llama-3.2-3B-Instruct |
| Nvidia Nemotron Nano 9B V2 | NVIDIA | 131K | $0.06 | $0.25 | together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2 |
| Mistral Small 3 | Mistral | 33K | $0.10 | $0.30 | together_ai/mistralai/Mistral-Small-24B-Instruct-2501 |
| Qwen 2.1 5B Instruct | Alibaba | 33K | $0.10 | $0.10 | together_ai/arize-ai/qwen-2-1.5b-instruct |
| Together Ai Up To 4B | Other | n/a | $0.10 | $0.10 | together-ai-up-to-4b |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.14 | $0.28 | together_ai/deepseek-ai/DeepSeek-V4-Flash-0731 |
| GLM 5.3 Flash | Zhipu | 1M | $0.15 | $0.50 | together_ai/zai-org/GLM-5.3-Flash |
| gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | together_ai/openai/gpt-oss-120b |
| Qwen3 Next 80B A3B Instruct | Alibaba | 262K | $0.15 | $1.50 | together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct |
| Qwen3 Next 80B A3B Thinking | Alibaba | 262K | $0.15 | $1.50 | together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking |
| Qwen3.8 Flash | Alibaba | 1M | $0.15 | $0.47 | together_ai/Qwen/Qwen3.8-Flash |
| Qwen3.5-9B | Alibaba | 262K | $0.17 | $0.25 | together_ai/Qwen/Qwen3.5-9B |
| DeepSeek R1 Distill Qwen 1 5B | DeepSeek | 131K | $0.18 | $0.18 | together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
| Llama 3.1 8B Instruct Turbo | Meta | 131K | $0.18 | $0.18 | together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo |
| Llama 4 Scout 17B 16e Instruct | Meta | 10.5M | $0.18 | $0.59 | together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct |
| Qwen3 VL 8B Instruct | Alibaba | 262K | $0.18 | $0.68 | together_ai/Qwen/Qwen3-VL-8B-Instruct |
| GLM 4.5 Air FP8 | Zhipu | 131K | $0.20 | $1.10 | together_ai/zai-org/GLM-4.5-Air-FP8 |
| Llama 3 8B Chat HF | Meta | 8K | $0.20 | $0.20 | together_ai/meta-llama/Llama-3-8b-chat-hf |
| Llama 3 8B Instruct | Meta | 8K | $0.20 | $0.20 | together_ai/meta-llama/Meta-Llama-3-8B-Instruct |
| Llama 3.1 8B | Meta | 131K | $0.20 | $0.20 | together_ai/meta-llama/Meta-Llama-3.1-8B |
| Llama Guard 4 12B | Meta | 164K | $0.20 | $0.20 | together_ai/meta-llama/Llama-Guard-4-12B |
| Ministral 3 14B Instruct 2512 | Mistral | 262K | $0.20 | $0.20 | together_ai/mistralai/Ministral-3-14B-Instruct-2512 |
| Mistral 7B Instruct V0.1 | Mistral | 33K | $0.20 | $0.20 | together_ai/mistralai/Mistral-7B-Instruct-v0.1 |
| Mistral 7B Instruct V0.3 | Mistral | 127K | $0.20 | $0.20 | together_ai/mistralai/Mistral-7B-Instruct-v0.3 |
| Qwen3 235B A22b FP8 Tput | Alibaba | 40K | $0.20 | $0.60 | together_ai/Qwen/Qwen3-235B-A22B-fp8-tput |
| Qwen3 235B A22b Instruct 2507 Tput | Alibaba | 262K | $0.20 | $6.00 | together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput |
| Together Ai 4 1B 8B | Other | n/a | $0.20 | $0.20 | together-ai-4.1b-8b |
| Llama 4 Maverick 17B 128e Instruct FP8 | Meta | 1M | $0.27 | $0.85 | together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 |
| Pearl: gemma-4-31b-it | Pearl | 262K | $0.28 | $0.86 | together_ai/pearl-ai/gemma-4-31b-it |
| DeepSeek V4.1 Flash | DeepSeek | 1M | $0.30 | $1.20 | together_ai/deepseek-ai/DeepSeek-V4.1-Flash |
| MiniMax M2.7 | MiniMax | 1M | $0.30 | $1.20 | together_ai/MiniMaxAI/MiniMax-M2.7 |
| MiniMax M3 | MiniMax | 1M | $0.30 | $1.20 | together_ai/MiniMaxAI/MiniMax-M3 |
| Qwen2 5 7B Instruct Turbo | Alibaba | 33K | $0.30 | $0.30 | together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo |
| Together Ai 8 1B 21B | Other | n/a | $0.30 | $0.30 | together-ai-8.1b-21b |
| Qwen3.7 Plus | Alibaba | 1M | $0.32 | $1.28 | together_ai/Qwen/Qwen3.7-Plus |
| Muse Glimmer 30B | Other | 131K | $0.35 | $1.50 | together_ai/meta-models/Muse-Glimmer-30B |
| Gemma 4 31B | 262K | $0.39 | $0.97 | together_ai/google/gemma-4-31B-it | |
| GLM 4.7 | Zhipu | 205K | $0.45 | $2.00 | together_ai/zai-org/GLM-4.7 |
| Inkling Small | Thinking Machines | 1M | $0.50 | $1.20 | together_ai/thinkingmachines/Inkling-Small |
| Kimi K2.5 | Moonshot | 262K | $0.50 | $2.80 | together_ai/moonshotai/Kimi-K2.5 |
| Kimi K2.5 Fp4 | Moonshot | 262K | $0.50 | $2.80 | together_ai/moonshotai/Kimi-K2.5-fp4 |
| Qwen3 Coder Next FP8 | Alibaba | 262K | $0.50 | $1.20 | together_ai/Qwen/Qwen3-Coder-Next-FP8 |
| Qwen3 VL 32B Instruct | Alibaba | 262K | $0.50 | $1.50 | together_ai/Qwen/Qwen3-VL-32B-Instruct |
| Qwen3.6 Plus | Alibaba | 1M | $0.50 | $3.00 | together_ai/Qwen/Qwen3.6-Plus |
1–50 of 99
Page 1 of 2
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 15 prices older, back to Sep 22, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI