The Orchestrator › Models › NVIDIA
NVIDIA: nvidia/Nemotron-3.5-Lightning-30B-A3B
nvidia/Nemotron-3.5-Lightning-30B-A3B via TrustedRouter
Specifications
| Provider | NVIDIA |
| Model ID | nvidia/nemotron-3.5-lightning-30b-a3b |
| Context window | 262K tokens (262,144) |
| Modalities | text → text |
| Tokenizer | unknown |
| Router sources | TrustedRouter |
| Released | — |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | TrustedRouter | nvidia/nemotron-3.5-lightning-30b-a3b | $0.053 | $0.211 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.053 | $0.211 | 262K |
Capabilities
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
tools, tool_choice, parallel_tool_calls, max_tokens, max_completion_tokens, temperature, top_p, top_k, min_p, reasoning, reasoning_effort, structured_outputs, response_format, stop, frequency_penalty, presence_penalty, repetition_penalty, seed, logit_bias, logprobs, top_logprobs, verbosity, background, cache_salt, chat_template, chat_template_kwargs, conversation, include, include_stop_str_in_output, instructions, max_output_tokens, max_tool_calls, metadata, previous_response_id, prompt_cache_key, safety_identifier, service_tier, skip_special_tokens, stop_sequences, store, thinking, truncation, user