Together AI API pricing
50 Together AI models, in US dollars per million tokens. Updated Oct 28, 2026.
50 models
| Model | Input | Cached input | Output | Context | Notes |
|---|---|---|---|---|---|
| arcee-ai/trinity-mini | $0.045 | — | $0.15 | 128K | |
| arize-ai/qwen-2-1.5b-instruct | $0.10 | — | $0.10 | 33K | |
| BAAI/bge-base-en-v1.5 | $0.008 | — | — | 1K | Embedding |
| deepseek-ai/DeepSeek-R1-0528 | $3.00 | — | $7.00 | 164K | |
| deepseek-ai/DeepSeek-V3 | $1.25 | — | $1.25 | 66K | |
| deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $0.13 | $3.96 | 1.05M | |
| deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $0.006 | $1.20 | 1.05M | |
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | $0.30 | $0.006 | $1.20 | 1.05M | |
| meta-llama/Llama-3.1-405B-Instruct | $3.50 | — | $3.50 | 4K | |
| meta-llama/Llama-3.2-1B-Instruct | $0.06 | — | $0.06 | 131K | |
| meta-llama/Llama-3.2-3B-Instruct | $0.06 | — | $0.06 | 131K | |
| meta-llama/Meta-Llama-3.1-8B | $0.20 | — | $0.20 | 16K | |
| meta-models/Muse-Glimmer-30B | $0.35 | $0.04 | $1.50 | 131K | |
| meta-models/Muse-Spark-Open-816B-A42B | $1.25 | $0.15 | $4.25 | 1.05M | |
| MiniMaxAI/MiniMax-M2.7 | $0.30 | $0.06 | $1.20 | 197K | |
| MiniMaxAI/MiniMax-M3 | $0.30 | $0.06 | $1.20 | 524K | Retires Nov 6, 2026 |
| MiniMaxAI/MiniMax-M3.1-Flash | $0.15 | $0.015 | $0.60 | 1.05M | |
| mistralai/Ministral-3-14B-Instruct-2512 | $0.20 | — | $0.20 | 262K | |
| mistralai/Mistral-7B-Instruct-v0.3 | $0.20 | — | $0.20 | 33K | |
| moonshotai/Kimi-K2-Instruct | $1.00 | — | $3.00 | — | |
| moonshotai/Kimi-K2.5-fp4 | $0.50 | — | $2.80 | 262K | |
| moonshotai/Kimi-K3 | $3.00 | $0.30 | $15.00 | 1.05M | |
| nvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.15 | $0.02 | $0.50 | 262K | |
| openai/gpt-oss-120b | $0.15 | — | $0.60 | 131K | |
| Prism-ML/Ternary-Bonsai-27B | $0 | — | $0 | 262K | |
| Qwen/Qwen2-1.5B-Instruct | $0.02 | — | $0.02 | 33K | |
| Qwen/Qwen2.5-14B-Instruct | $0.80 | — | $0.80 | 33K | |
| Qwen/Qwen2.5-72B-Instruct | $1.20 | — | $1.20 | 33K | |
| Qwen/Qwen2.5-7B-Instruct-Turbo | $0.30 | — | $0.30 | 33K | |
| Qwen/Qwen3.5-9B | $0.17 | — | $0.25 | 262K | |
| Qwen/Qwen3.6-Plus | $0.50 | — | $3.00 | 1M | |
| Qwen/Qwen3.7-Max | $1.50 | $0.30 | $4.50 | 1M | |
| Qwen/Qwen3.7-Plus | $0.32 | — | $1.28 | 1M | |
| Qwen/Qwen3.8-2.4T-A95B | $2.00 | $0.25 | $6.00 | 1.01M | |
| Qwen/Qwen3.8-Flash | $0.15 | — | $0.47 | 1M | |
| reflection/Beam-1.0-501B-A23B | $0.40 | $0.04 | $1.20 | 1.05M | |
| thinkingmachines/Inkling | $1.00 | $0.17 | $4.05 | 524K | Retires Nov 6, 2026 |
| together-ai-21.1b-41b | $0.80 | — | $0.80 | — | |
| together-ai-4.1b-8b | $0.20 | — | $0.20 | — | |
| together-ai-41.1b-80b | $0.90 | — | $0.90 | — | |
| together-ai-8.1b-21b | $0.30 | — | $0.30 | 1K | |
| together-ai-81.1b-110b | $1.80 | — | $1.80 | — | |
| together-ai-embedding-151m-to-350m | $0.016 | — | — | — | Embedding |
| together-ai-embedding-up-to-150m | $0.008 | — | — | — | Embedding |
| together-ai-up-to-4b | $0.10 | — | $0.10 | — | |
| together/Tev1-4B-experimental | $0.042 | — | $0 | 33K | |
| zai-org/GLM-4.6 | $0.60 | — | $2.20 | 203K | |
| zai-org/GLM-5.2 | $1.40 | $0.26 | $4.40 | 1.05M | |
| zai-org/GLM-5.3 | $1.40 | $0.26 | $4.40 | 1.05M | |
| zai-org/GLM-5.3-Flash | $0.15 | $0.03 | $0.50 | 1.05M |
See what your Together AI calls actually cost, by service, model and customer, priced for where each call ran.
Get started freeList prices from LiteLLM's public price file. Long-prompt, batch and priority rates aren't shown; check Together AI's pricing page before you commit to a budget. All providers