Ratesper 1M tokens
| Input | $0.60 |
| Output | $3.60 |
| Cache Read | $0.20 |
Estimate Your Monthly Cost
A request with input and output tokens, requests / month at a % cache hit rate $114.00/mo
Compare all models at this workload →Excludes cache writes and batch discounts.
Route Comparisonper 1M tokens
| Route | Input | Output | Cache Read |
|---|---|---|---|
| Direct — Together AIverified 2026-07-10 | $0.60 | $3.60 | $0.20 |
| via OpenRouterverified 2026-07-07 | $0.50 | $2.20 | $0.10 |
OpenRouter adds a 5.5% platform fee on pay-as-you-go credits (verified 2026-07-08).
Specifications
| API Model ID | nvidia/nemotron-3-ultra-550b-a55b |
| Context Window | 512.3K tokens |
Modalitiestext
Capabilitiestool-use · streaming · json-mode · reasoning
More Together AI Text / Chat Models
LFM2-24B-A2B · MiniMax M2.7 · MiniMax M3 · Qwen 2.5 7B Instruct Turbo · Qwen3 235B A22B Instruct 2507 · Qwen3.5 397B A17B · Qwen3.5 9B · Qwen3.6 Plus · Qwen3.7 Max · Qwen3.7 Plus · Cogito v2.1 671B · DeepSeek V4 Pro · RNJ-1 Instruct · Gemma 3n E4B Instruct · Gemma 4 31B Instruct · Llama 3.3 70B · Meta Llama 3 8B Instruct Lite · Kimi K2.6 · Kimi K2.7 Code · GPT-OSS 120B · GPT-OSS 20B · Gemma 4 31B Instruct (Pearl AI) · GLM-5.1 · GLM-5.2 ·