Reference

Available models

A production model quick reference and the authoritative way to list models available to a key.

Model availability differs by plan key. The list below is a quick reference for common production models, not a replacement for dynamic discovery. See the pricing catalog API for the full public catalog and benchmark prices. The authoritative callable set is the current key's GET /v1/models response.

curl https://api.hop-base.com/v1/models \
  -H "Authorization: Bearer sk-your-key"

OpenAI chat and reasoning

  • gpt-5.6-sol / gpt-5.6-terra / gpt-5.6-luna: flagship / balanced / lightweight
  • gpt-5.5: complex reasoning and Codex
  • gpt-5.4: balanced performance
  • gpt-5.4-mini: low latency and cost
  • gpt-5.3-codex-spark: lightweight Codex tasks
  • codex-auto-review: automated code review

OpenAI image

  • gpt-image-2: Image 2.0

Use POST /v1/images/generations. Supports auto, 1K, 2K, and 4K sizes.

Gemini chat and reasoning

  • gemini-omni-flash-preview: text, image, and video input; 3-10 second video output
  • gemini-3.6-flash: latest general-purpose Flash model
  • gemini-3.1-pro-preview
  • gemini-3.1-pro-preview-customtools
  • Other Gemini 2.5-3.5 Pro, Flash, and Flash-Lite models

Standard chat uses POST /v1/chat/completions; Omni's complete multimodal API uses POST /v1/interactions.

Seedream image

  • seedream-5-0-pro: 1K / 2K text-to-image, image-to-image, and editing

Uses the OpenAI Images protocol. Signed image URLs are valid for 24 hours.

Gemini image

  • gemini-2.5-flash-image: Banana, 1K
  • gemini-3-pro-image*: Banana Pro family, 1K / 2K / 4K
  • gemini-3.1-flash-image*: Banana 2 family, 1K / 2K
  • gemini-3.1-flash-lite-image: Banana 2 Lite, 1K

* abbreviates a family here and is not a requestable model ID. Use the complete ID returned by GET /v1/models.

GLM chat and reasoning

  • glm-5.2
  • glm-5.2-fp8

Uses OpenAI Chat Completions. In client advanced settings, choose "OpenAI Chat Completions (routing required)."

Claude multimodal

  • claude-fable-5: latest reasoning flagship
  • claude-opus-4-8
  • claude-opus-4-7
  • claude-opus-4-6
  • claude-opus-4-5-20251101, short name claude-opus-4-5
  • claude-sonnet-5: next-generation Sonnet
  • claude-sonnet-4-6
  • claude-sonnet-4-5-20250929, short name claude-sonnet-4-5
  • claude-haiku-4-5-20251001, short name claude-haiku-4-5

Seedance video

  • dreamina-seedance-2-0-*: standard
  • dreamina-seedance-2-0-fast-*: fast
  • dreamina-seedance-2-0-mini-*: mini

Use the complete ID returned by /v1/models. See Video generation for integration and pricing.

Query Claude models with a Claude plan key. Codex and OpenAI keys do not return Claude models. Never assume that separate plan groups share a model list.