Together AI is a cloud platform that resells models with its own infrastructure, billing and regional hosting. Its prices tend to track the first-party rate, with the platform's own quotas and service-level terms attached.
It lists 33 models on this page. Coverage spans text and chat (33). The lowest-priced model hosted here is LFM2 24B A2B.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| LFM2 24B A2BLiquidAI/LFM2-24B-A2BOnly channel | $0.03 | $0.12 | — | 32,768 | Only channel |
| Rnj-1 Instructessentialai/Rnj-1-InstructOnly channel | $0.15 | $0.15 | — | 32,768 | Only channel |
| DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-07313.5× pricier | $0.14 | $0.28 | $0.03 | 1,048,576 | 3.5× pricier |
| Qwen3.5 9BQwen/Qwen3.5-9B1.9× pricier | $0.17 | $0.25 | — | 262,144 | 1.9× pricier |
| GLM-5.3-Flashzai-org/GLM-5.3-Flash4.8× pricier | $0.15 | $0.50 | $0.03 | 1,048,575 | 4.8× pricier |
| Nemotron 3.5 Super VL 120B A12Bnvidia/NVIDIA-Nemotron-3.5-Super-VL1.8× pricier | $0.15 | $0.50 | $0.02 | 262,144 | 1.8× pricier |
| GPT OSS 120Bopenai/gpt-oss-120b4.5× pricier | $0.15 | $0.60 | — | 131,072 | 4.5× pricier |
| Qwen2.5 7B InstructQwen/Qwen2.5-7B-Instruct-Turbo6.0× pricier | $0.30 | $0.30 | — | 32,768 | 6.0× pricier |
| Qwen3 235B-A22B Instruct 2507Qwen/Qwen3-235B-A22B-Instruct-2507-tput3.2× pricier | $0.20 | $0.60 | — | 262,144 | 3.2× pricier |
| DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash10.0× pricier | $0.30 | $1.20 | $0.006 | 1,048,576 | 10.0× pricier |
| MiniMax-M3MiniMaxAI/MiniMax-M31.4× pricier | $0.30 | $1.20 | $0.06 | 524,288 | 1.4× pricier |
| MiniMax-M2.7MiniMaxAI/MiniMax-M2.72.6× pricier | $0.30 | $1.20 | $0.06 | 196,608 | 2.6× pricier |
| MiniMax-M2.5MiniMaxAI/MiniMax-M2.51.4× pricier | $0.30 | $1.20 | $0.06 | 204,800 | 1.4× pricier |
| Beam 1.0 501B A23Breflection/Beam-1.0-501B-A23B1.4× pricier | $0.40 | $1.20 | $0.04 | 1,048,576 | 1.4× pricier |
| Qwen3 Coder NextQwen/Qwen3-Coder-Next-FP82.8× pricier | $0.50 | $1.20 | — | 262,144 | 2.8× pricier |
| DeepSeek-V3.1deepseek-ai/DeepSeek-V3-12.7× pricier | $0.60 | $1.70 | — | 131,072 | 2.7× pricier |
| Llama-3.3-70B-Instructmeta-llama/Llama-3.3-70B-Instruct-Turbo10.9× pricier | $1.04 | $1.04 | — | 131,072 | 10.9× pricier |
| Qwen3.6 PlusQwen/Qwen3.6-Plus1.9× pricier | $0.50 | $3.00 | — | 1,000,000 | 1.9× pricier |
| DeepSeek-V3deepseek-ai/DeepSeek-V32.7× pricier | $1.25 | $1.25 | — | 131,072 | 2.7× pricier |
| Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B3.6× pricier | $0.60 | $3.60 | $0.35 | 262,144 | 3.6× pricier |
| Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b13.5× pricier | $0.60 | $3.60 | $0.20 | 512,300 | 13.5× pricier |
| GLM-5zai-org/GLM-52.1× pricier | $1.00 | $3.20 | — | 202,752 | 2.1× pricier |
| Inklingthinkingmachines/Inkling1.0× pricier | $1.00 | $4.05 | $0.17 | 524,288 | 1.0× pricier |
| DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-08132.2× pricier | $1.32 | $3.96 | $0.13 | 1,048,576 | 2.2× pricier |
| Muse Spark Openmeta-models/Muse-Spark-Open-816B-A42B1.1× pricier | $1.25 | $4.25 | $0.15 | 1,048,576 | 1.1× pricier |
| Qwen3-Coder 480B-A35B InstructQwen/Qwen3-Coder-480B-A35B-Instruct-FP89.0× pricier | $2.00 | $2.00 | — | 262,144 | 9.0× pricier |
| GLM-5.3zai-org/GLM-5.36.3× pricier | $1.40 | $4.40 | $0.26 | 1,048,575 | 6.3× pricier |
| GLM-5.2zai-org/GLM-5.23.3× pricier | $1.40 | $4.40 | $0.26 | 1,048,575 | 3.3× pricier |
| GLM-5.1zai-org/GLM-5.12.0× pricier | $1.40 | $4.40 | $0.26 | 202,752 | 2.0× pricier |
| Qwen3.7 MaxQwen/Qwen3.7-Max3.0× pricier | $2.50 | $7.50 | $0.50 | 1,000,000 | 3.0× pricier |
| Kimi K3.1 Promoonshotai/Kimi-K3.1-Pro1.7× pricier | $2.00 | $10.00 | $0.20 | 1,048,576 | 1.7× pricier |
| DeepSeek-R1deepseek-ai/DeepSeek-R14.2× pricier | $3.00 | $7.00 | — | 163,839 | 4.2× pricier |
| Kimi K3moonshotai/Kimi-K33.3× pricier | $3.00 | $15.00 | $0.30 | 1,048,576 | 3.3× pricier |