PROVIDER / MODEL PUBLISHER

OpenAI

Hosted model APIs with dated snapshots and distinct endpoint formats. Confirm current lifecycle and service terms.

Official documentation ↗
HOSTED API

GPT-6.1 Sol↗

A September 2026 release for complex coding and professional work, available through Responses and Chat Completions.

OpenAI directs tool-calling workflows to the Responses API. Record the service tier and reasoning setting; Ultrafast mode was added on October 8, 2026.

HOSTED API

GPT-6 Luna↗

A September 2026 reasoning model with text and image inputs and text output.

Responses and Chat Completions are supported; the Decisions API was added in beta on October 6, 2026. Evaluate that endpoint separately and recheck prices and token tiers.

HOSTED API

GPT-6 Sol↗

A September 2026 reasoning model with text and image inputs, introduced alongside GPT-6 Luna.

Distinguish GPT-6 Sol from the later GPT-6.1 Sol release. Pricing depends on input length, caching and processing tier; keep those choices in the evaluation record.

HOSTED API

GPT-6 Astra↗

A September 2026 GPT release for demanding work across reasoning, coding, computer use, research and documents.

GPT-6 Astra does not support none reasoning effort, custom temperature, top_p or logprobs. Check your request adapter before replaying prompts from earlier models.

HOSTED API

GPT Image 2.5 Flare↗

A September 2026 image generation and editing release, positioned for everyday image workflows.

Image API and Responses image-generation tool behavior can differ. Record quality setting, output size, edits and total billing; a text-model token estimate is insufficient.

HOSTED API

GPT Image 2.5 Sunburst↗

A September 2026 image generation and editing release, positioned for editing precision.

The provider positioning is a hypothesis to test. Compare preservation of unchanged image regions and instruction compliance at the same output size and quality setting.

HOSTED API

GPT-4.1↗

A hosted model family introduced for coding and instruction following.

Use a dated model snapshot for reproducible API comparisons. Responses and Chat Completions have different request shapes.

Keep publisher, model and endpoint separate

The publisher identifies the model family or checkpoint. An inference operator selects a runtime, quantization and service configuration. The API endpoint defines the accepted request shape and operational limits. Compare all three when planning a migration.

Track lifecycle changes

Official release notes can announce previews, general availability, retirement and alias changes. A model appearing in an API list is an observation of access, not necessarily a new public release.

Open the release radar →