Together AI API Pricing (Oct 2026): All 85 Models per 1M Tokens
As of : 85 models tracked. The median price is $0.50 per 1M input tokens and $1.15 per 1M output tokens. Cheapest blended price: Qwen2-1.5B-Instruct (Together AI, $0.02 per 1M input / $0.02 per 1M output).
API list prices for every Together AI chat model we track.
Models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| Qwen2-1.5B-Instruct | Together AI | $0.02 | $0.02 | — | 33K |
| Tev1-4B-experimental | Together AI | $0.04 | — | — | 33K |
| Llama-3.2-1B-Instruct | Together AI | $0.06 | $0.06 | — | 131K |
| Llama-3.2-3B-Instruct | Together AI | $0.06 | $0.06 | — | 131K |
| trinity-mini | Together AI | $0.04 | $0.15 | — | 128K |
| gpt-oss-20b | Together AI | $0.05 | $0.20 | — | 131K |
| qwen-2-1.5b-instruct | Together AI | $0.10 | $0.10 | — | 33K |
| together-ai-up-to-4b | Together AI | $0.10 | $0.10 | — | — |
| NVIDIA-Nemotron-Nano-9B-v2 | Together AI | $0.06 | $0.25 | — | 131K |
| Mistral-Small-24B-Instruct-2501 | Together AI | $0.10 | $0.30 | — | 33K |
| DeepSeek-V4-Flash-0731 | Together AI | $0.14 | $0.28 | $0.03 | 1.04858M |
| DeepSeek-R1-Distill-Qwen-1.5B | Together AI | $0.18 | $0.18 | — | 131K |
| Meta-Llama-3.1-8B-Instruct-Turbo | Together AI | $0.18 | $0.18 | — | 131K |
| Qwen3.5-9B | Together AI | $0.17 | $0.25 | — | 262K |
| Llama-3-8b-chat-hf | Together AI | $0.20 | $0.20 | — | 8K |
| Meta-Llama-3-8B-Instruct | Together AI | $0.20 | $0.20 | — | 8K |
| Ministral-3-14B-Instruct-2512 | Together AI | $0.20 | $0.20 | — | 262K |
| Mistral-7B-Instruct-v0.1 | Together AI | $0.20 | $0.20 | — | 33K |
| Mistral-7B-Instruct-v0.3 | Together AI | $0.20 | $0.20 | — | 33K |
| together-ai-4.1b-8b | Together AI | $0.20 | $0.20 | — | — |
| Qwen3.8-Flash | Together AI | $0.15 | $0.47 | — | 1M |
| NVIDIA-Nemotron-3.5-Super-VL | Together AI | $0.15 | $0.50 | $0.02 | 262K |
| GLM-5.3-Flash | Together AI | $0.15 | $0.50 | $0.03 | 1.04858M |
| gpt-oss-120b | Together AI | $0.15 | $0.60 | — | 131K |
| Llama-4-Scout-17B-16E-Instruct | Together AI | $0.18 | $0.59 | — | 1.04858M |
| Qwen2.5-7B-Instruct-Turbo | Together AI | $0.30 | $0.30 | — | 33K |
| together-ai-8.1b-21b | Together AI | $0.30 | $0.30 | — | 1K |
| Qwen3-VL-8B-Instruct | Together AI | $0.18 | $0.68 | — | 262K |
| GLM-4.5-Air-FP8 | Together AI | $0.20 | $1.10 | — | 131K |
| Qwen3-Next-80B-A3B-Instruct | Together AI | $0.15 | $1.50 | — | 262K |
| Qwen3-Next-80B-A3B-Thinking | Together AI | $0.15 | $1.50 | — | 262K |
| MiniMax-M2.7 | Together AI | $0.30 | $1.20 | $0.06 | 197K |
| MiniMax-M3 | Together AI | $0.30 | $1.20 | $0.06 | 524K |
| DeepSeek-V4.1-Flash | Together AI | $0.30 | $1.20 | $0.006 | 1.04858M |
| gemma-4-31B-it | Together AI | $0.39 | $0.97 | — | 262K |
| Qwen3.7-Plus | Together AI | $0.32 | $1.28 | — | 1M |
| Nous-Hermes-2-Mixtral-8x7B-DPO | Together AI | $0.60 | $0.60 | — | 33K |
| Mixtral-8x7B-Instruct-v0.1 | Together AI | $0.60 | $0.60 | — | 33K |
| Beam-1.0-501B-A23B | Together AI | $0.40 | $1.20 | $0.04 | 1.04858M |
| Muse-Glimmer-30B | Together AI | $0.35 | $1.50 | $0.04 | 131K |
| Qwen3-Coder-Next-FP8 | Together AI | $0.50 | $1.20 | — | 262K |
| Qwen3-VL-32B-Instruct | Together AI | $0.50 | $1.50 | — | 262K |
| Qwen2.5-14B-Instruct | Together AI | $0.80 | $0.80 | — | 33K |
| Qwen2.5-Coder-32B-Instruct | Together AI | $0.80 | $0.80 | — | 16K |
| deepseek-coder-33b-instruct | Together AI | $0.80 | $0.80 | — | 16K |
| gemma-2-27b-it | Together AI | $0.80 | $0.80 | — | 8K |
| together-ai-21.1b-41b | Together AI | $0.80 | $0.80 | — | — |
| GLM-4.7 | Together AI | $0.45 | $2.00 | — | 203K |
| DeepSeek-V3.1 | Together AI | $0.60 | $1.70 | — | 131K |
| Meta-Llama-3-70B-Instruct-Turbo | Together AI | $0.88 | $0.88 | — | 8K |
| Meta-Llama-3.1-70B-Instruct-Turbo | Together AI | $0.88 | $0.88 | — | 131K |
| Llama-3.1-Nemotron-70B-Instruct-HF | Together AI | $0.88 | $0.88 | — | 33K |
| Qwen2-72B-Instruct | Together AI | $0.90 | $0.90 | — | 33K |
| together-ai-41.1b-80b | Together AI | $0.90 | $0.90 | — | — |
| GLM-4.6 | Together AI | $0.60 | $2.20 | — | 203K |
| Llama-3.3-70B-Instruct-Turbo | Together AI | $1.04 | $1.04 | — | 131K |
| Kimi-K2.5-fp4 | Together AI | $0.50 | $2.80 | — | 262K |
| Qwen3.6-Plus | Together AI | $0.50 | $3.00 | — | 1M |
| QwQ-32B | Together AI | $1.20 | $1.20 | — | 131K |
| Qwen2-VL-72B-Instruct | Together AI | $1.20 | $1.20 | — | 33K |
| Qwen2.5-72B-Instruct | Together AI | $1.20 | $1.20 | — | 33K |
| Qwen2.5-72B-Instruct-Turbo | Together AI | $1.20 | $1.20 | — | 131K |
| DeepSeek-V3 | Together AI | $1.25 | $1.25 | — | 66K |
| Qwen3.5-397B-A17B | Together AI | $0.60 | $3.60 | $0.35 | 262K |
| nemotron-3-ultra-550b-a55b | Together AI | $0.60 | $3.60 | $0.20 | 512K |
| Kimi-K2-Instruct | Together AI | $1.00 | $3.00 | — | — |
| GLM-5 | Together AI | $1.00 | $3.20 | — | 203K |
| DeepSeek-R1-Distill-Qwen-14B | Together AI | $1.60 | $1.60 | — | 131K |
| Kimi-K2.7-Code | Together AI | $0.95 | $4.00 | $0.19 | 262K |
| Inkling | Together AI | $1.00 | $4.05 | $0.17 | 524K |
| together-ai-81.1b-110b | Together AI | $1.80 | $1.80 | — | — |
| DeepSeek-V4-Pro-0813 | Together AI | $1.32 | $3.96 | $0.13 | 1.04858M |
| Qwen3-Coder-480B-A35B-Instruct-FP8 | Together AI | $2.00 | $2.00 | — | 262K |
| DeepSeek-R1-Distill-Llama-70B | Together AI | $2.00 | $2.00 | — | 131K |
| Muse-Spark-Open-816B-A42B | Together AI | $1.25 | $4.25 | $0.15 | 1.04858M |
| Kimi-K2.6 | Together AI | $1.20 | $4.50 | $0.20 | 262K |
| GLM-5.1 | Together AI | $1.40 | $4.40 | $0.26 | 203K |
| GLM-5.2 | Together AI | $1.40 | $4.40 | $0.26 | 1.04858M |
| GLM-5.3 | Together AI | $1.40 | $4.40 | $0.26 | 1.04858M |
| Qwen3.7-Max | Together AI | $1.50 | $4.50 | $0.30 | 1M |
| Qwen3.8-2.4T-A95B | Together AI | $2.00 | $6.00 | $0.25 | 1.01M |
| Qwen2.5-VL-72B-Instruct | Together AI | $1.95 | $8.00 | — | 33K |
| Llama-3.1-405B-Instruct | Together AI | $3.50 | $3.50 | — | 4K |
| DeepSeek-R1-0528 | Together AI | $3.00 | $7.00 | — | 164K |
| Kimi-K3 | Together AI | $3.00 | $15.00 | $0.30 | 1.04858M |
FAQ
How are prices shown?
In US dollars per 1 million tokens, as listed for each model's API. 'Blended' assumes 3 input tokens for every output token.
Which model is cheapest here?
Qwen2-1.5B-Instruct from Together AI, at $0.02 per 1M input and $0.02 per 1M output tokens (as of ).
How current are these prices?
We copy the open-source LiteLLM price list once a day and record every change. Providers can change prices at any time, so confirm on the official pricing page linked from each model.