TRtrajectory
training

Get Training Options Route

Changed on

Return supported training models and their authored option ranges.

get/api/v1/train/options

Request

  • Base URL
    https://api.trajectory.ai (the document declares no server; this is the origin it was published from)
  • URL
    https://api.trajectory.ai/api/v1/train/options
  • Auth
    none declared

Query parameters

bench_idstring required
base_model_slug'thinkingmachines/Inkling-Small' | 'Qwen/Qwen3.5-4B' | 'Qwen/Qwen3.5-397B-A17B' | 'Qwen/Qwen3.6-35B-A3B' | 'Qwen/Qwen3.8-27B' | 'nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16' | 'nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16' | 'nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16' | 'nvidia/NVIDIA-Nemotron-3.5-Super-120B-A12B-BF16' | 'openai/gpt-6.1-sol' | 'openai/gpt-6-sol' | 'openai/gpt-6-astra' | 'openai/gpt-5.6-sol' | 'openai/gpt-5.6-luna' | 'anthropic/claude-opus-5.5' | 'anthropic/claude-sonnet-5.5' | 'openai/gpt-5-mini' | 'openai/gpt-5.4-mini' | 'openai/gpt-5.5' | 'anthropic/claude-sonnet-4.6' | 'google/gemini-3.1-pro-preview' | 'z-ai/glm-5.3' | 'z-ai/glm-5.3-flash' | 'moonshotai/kimi-k3'

Response

Successful Response

bench_idstring required

Changes

  • 5b5a8ae4b4a4Revision changes
    • warning

      added the new val_max_output_tokens_per_trajectory enum value to the /// response property for the response status

    • warning

      added the new val_max_output_tokens_per_turn enum value to the /// response property for the response status

    • warning

      added the new val_max_turns_per_trajectory enum value to the /// response property for the response status

    • warning

      added the new val_trajectory_timeout_seconds enum value to the /// response property for the response status

  • ac63eff4913fRevision changes
    • warning

      added the new batch_size enum value to the /// response property for the response status

    • warning

      added the new batch_timeout_seconds enum value to the /// response property for the response status

    • warning

      added the new density_aware_training enum value to the /// response property for the response status

    • warning

      added the new lr_min_ratio enum value to the /// response property for the response status

    • warning

      added the new max_concurrent_trajectories enum value to the /// response property for the response status

    • warning

      added the new max_output_tokens_per_trajectory enum value to the /// response property for the response status

    • warning

      added the new max_output_tokens_per_turn enum value to the /// response property for the response status

    • warning

      added the new max_staleness enum value to the /// response property for the response status

    • warning

      added the new min_trajectories_per_group enum value to the /// response property for the response status

    • warning

      added the new train_on_all_fail enum value to the /// response property for the response status

    • warning

      added the new train_on_all_pass enum value to the /// response property for the response status

    • warning

      added the new train_on_zero_advantage enum value to the /// response property for the response status

    • warning

      added the new trajectory_timeout_seconds enum value to the /// response property for the response status

    • warning

      added the new val_enabled enum value to the /// response property for the response status

    • warning

      added the new val_final_wait_timeout_seconds enum value to the /// response property for the response status

    • warning

      added the new val_interval_steps enum value to the /// response property for the response status

    • warning

      added the new val_max_concurrent_trajectories enum value to the /// response property for the response status

    • warning

      added the new val_num_tasks enum value to the /// response property for the response status

    • warning

      added the new val_reasoning_effort enum value to the /// response property for the response status

    • warning

      added the new val_temperature enum value to the /// response property for the response status

    • warning

      added the new val_top_k enum value to the /// response property for the response status

    • warning

      added the new val_top_p enum value to the /// response property for the response status

    • warning

      added the new val_trajectories_per_task enum value to the /// response property for the response status

    • info

      removed the batch_collection_idle_timeout_seconds enum value from the /// response property for the response status

    • info

      removed the evaluation_collection_timeout_seconds enum value from the /// response property for the response status

    • info

      removed the evaluation_enabled enum value from the /// response property for the response status

    • info

      removed the evaluation_frequency enum value from the /// response property for the response status

    • info

      removed the evaluation_max_active_rollouts enum value from the /// response property for the response status

    • info

      removed the evaluation_max_samples enum value from the /// response property for the response status

    • info

      removed the evaluation_reasoning_effort enum value from the /// response property for the response status

    • info

      removed the evaluation_samples_per_task enum value from the /// response property for the response status

    • info

      removed the evaluation_temperature enum value from the /// response property for the response status

    • info

      removed the evaluation_top_k enum value from the /// response property for the response status

    • info

      removed the evaluation_top_p enum value from the /// response property for the response status

    • info

      removed the execution_timeout_seconds enum value from the /// response property for the response status

    • info

      removed the intelligent_density_training enum value from the /// response property for the response status

    • info

      removed the max_active_rollouts enum value from the /// response property for the response status

    • info

      removed the max_output_tokens_per_step enum value from the /// response property for the response status

    • info

      removed the max_steps_off_policy enum value from the /// response property for the response status

    • info

      removed the max_total_tokens_per_trajectory enum value from the /// response property for the response status

    • info

      removed the min_lr_ratio enum value from the /// response property for the response status

    • info

      removed the min_samples_per_group enum value from the /// response property for the response status

    • info

      removed the reject_all_fail enum value from the /// response property for the response status

    • info

      removed the reject_all_pass enum value from the /// response property for the response status

    • info

      removed the reject_zero_advantage enum value from the /// response property for the response status

    • info

      removed the samples_per_instance enum value from the /// response property for the response status

    • info

      removed the train_batch_size enum value from the /// response property for the response status