Together AI API Pricing
🌍 GlobalPayment Methods
Together AI is an AI API relay service. ComputeUnion tracks 35 price records for this platform (35 auto-scraped, Updated 6m ago; 0 manually maintained). Browse the categories below to compare Together AI pricing across providers.
Model Pricing on Together AI
Prices per 1M tokens
LLM35 models
| Model | Input | Output | Context | Updated |
|---|---|---|---|---|
| LFM2 24B A2B | $0.0300 | $0.1200 | — | Updated 6m ago |
| gpt-oss-20B | $0.0500 | $0.2000 | — | Updated 6m ago |
| Gemma 3n E4B Instruct | $0.0600 | $0.1200 | — | Updated 6m ago |
| Llama 3 8B Instruct Lite | $0.1400 | $0.1400 | — | Updated 6m ago |
| gpt-oss-120B | $0.1500 | $0.6000 | — | Updated 6m ago |
| Rnj-1 Instruct | $0.1500 | $0.1500 | — | Updated 6m ago |
| Qwen3 235B A22B FP8 Throughput | $0.2000 | $0.6000 | — | Updated 6m ago |
| Qwen3 235B A22B Instruct 2507 FP8 Throughput | $0.2000 | $0.6000 | — | Updated 6m ago |
| Gemma-4-31B-it-Pearl | $0.2800 | $0.8600 | — | Updated 6m ago |
| MiniMax M3 | $0.3000 | $1.2000 | — | Updated 6m ago |
| Gemma 4 31B | $0.3900 | $0.9700 | — | Updated 6m ago |
| NVIDIA Nemotron 3 Ultra | $0.6000 | $3.6000 | — | Updated 6m ago |
| GLM-5 | $1.0000 | $3.2000 | — | Updated 6m ago |
| Cogito v2.1 671B | $2.1000 | $1.2500 | — | Updated 6m ago |
| DeepSeek V4 Pro | $2.1000 | $4.4000 | — | Updated 6m ago |
| Qwen2.5 7B Instruct Turbo | $2.5000 | $0.3000 | — | Updated 6m ago |
| MiniMax M2.5 | $2.5000 | $0.3000 | — | Updated 6m ago |
| Kimi K2.6 | $2.6000 | $1.2000 | — | Updated 6m ago |
| MiniMax M2.7 | $2.7000 | $0.3000 | — | Updated 6m ago |
| Llama 4 Scout Llama 4 Scout | $3.0000 | $7.5000 | — | Updated 6m ago |
| DeepSeek-R1 DeepSeek-R1-0528 DeepSeek-V3 DeepSeek-V3-0324 DeepSeek-V3.1 DeepSeek-V3.1-Base | $3.1000 | $10.0000 | — | Updated 6m ago |
| Llama 3.3 70B | $3.3000 | $1.0400 | — | Updated 6m ago |
| Qwen3.5-397B-A17B | $3.5000 | $0.6000 | — | Updated 6m ago |
| NVIDIA Nemotron 3.5 ASR | $3.5000 | $0.0045 | — | Updated 6m ago |
| Qwen3.5-122B-A10B | $3.5000 | $6.0000 | — | Updated 6m ago |
| Qwen3.5 9B | $3.5000 | $0.1700 | — | Updated 6m ago |
| Qwen3.6-Plus | $3.6000 | $0.5000 | — | Updated 6m ago |
| Qwen3.7-Max | $3.7000 | $1.2500 | — | Updated 6m ago |
| GLM-4.6 GLM-4.7 | $4.6000 | $9.0000 | — | Updated 6m ago |
| GLM-5.1 | $5.1000 | $1.4000 | — | Updated 6m ago |
| GLM-5 GLM-5.1 | $5.1000 | $5.1000 | — | Updated 6m ago |
| Qwen3-235B-A22B Qwen3-235B-A22B-Instruct-2507 | $6.0000 | $15.0000 | — | Updated 6m ago |
| Llama 4 Maverick Llama 4 Maverick Instruct | $8.0000 | $20.0000 | — | Updated 6m ago |
| Qwen3-Coder-480B-A35B-Instruct | $9.0000 | $22.5000 | — | Updated 6m ago |
| Kimi K2 Thinking Kimi K2 Instruct-0905 Kimi K2 Instruct Kimi K2 Base | $15.0000 | $37.5000 | — | Updated 6m ago |
FAQ
What is Together AI?
Together AI is an AI API relay service aggregating multi-provider access through a unified endpoint. ComputeUnion currently tracks 35 price records for this platform — 35 auto-scraped (Updated 6m ago), 0 manually maintained.
How does Together AI pricing compare to official providers?
Relay services like Together AI typically offer discounted rates versus official provider pricing, though latency and SLA terms may differ. Use the category links below to compare Together AI prices against other providers on ComputeUnion.
Is Together AI accessible from China?
Together AI is an international service — direct access from China mainland may be restricted.
Related pages