gpt-6.1-terraOpenAI model matrix
Choose the model type. Compare its position. See when it arrived.
A chronological view of the models in our directory, organized by what they do and where they fit.
Recent model landscape
10The 10 most recent dated models · time × selection tier
Swipe to explore the timeline. Tap a model for details.
Horizontal distance follows calendar time. Vertical bands are selection tiers, not benchmark scores; labels may occupy separate tracks within a tier. Select a model to inspect its source. 2 models without a date or tier are excluded.
Complete model matrix
Text
30 models shownDates follow official model or family announcements. API availability may differ; unverified records are labeled.
Scroll horizontally to compare tiers.
| Release month | FlagshipCapability first | MainstreamBalanced everyday workloads | ValueCost & throughput first |
|---|---|---|---|
| 2026101 models | — | View live pricing 922K tokensPricing ↗ | — |
| 2026094 models | — | gpt-6-lunaInput$0.08Output$0.4/ 1M tokens ValuePricing ↗ | |
| 2026073 models | gpt-5.6-solInput$2.6Output$13/ 1M tokens 922K tokensPricing ↗ | gpt-5.6-terraInput$1.3Output$7.8/ 1M tokens MainstreamPricing ↗ | gpt-5.6-lunaInput$0.16Output$0.96/ 1M tokens ValuePricing ↗ |
| 2026041 models | gpt-5.5Input$3.25Output$19.5/ 1M tokens 1M tokensPricing ↗ | — | — |
| 2026034 models | gpt-5.4Input$2Output$12/ 1M tokens 1M tokensPricing ↗ gpt-5.4-proFamily announcementReasoning Input$30Output$180/ 1M tokens FlagshipPricing ↗ | — | |
| 2026021 models | gpt-5.3-codexModel announcementCoding specialist Input$1.4Output$11.2/ 1M tokens 272K tokensPricing ↗ | — | — |
| 2025122 models | gpt-5.2-codexModel announcementCoding specialist Input$1.4Output$11.2/ 1M tokens FlagshipPricing ↗ gpt-5.2Input$1.75Output$14/ 1M tokens FlagshipPricing ↗ | — | — |
| 2025113 models | gpt-5.1-codexFamily announcementCoding specialist Input$1Output$8/ 1M tokens FlagshipPricing ↗ gpt-5.1Input$1Output$8/ 1M tokens FlagshipPricing ↗ | — | gpt-5.1-codex-miniFamily announcementCoding specialist Input$0.2Output$1.6/ 1M tokens ValuePricing ↗ |
| 2025101 models | — | — | |
| 2025091 models | gpt-5-codexModel announcementCoding specialist Input$1Output$8/ 1M tokens 272K tokensPricing ↗ | — | — |
| 2025083 models | gpt-5Input$1Output$8/ 1M tokens 272K tokensPricing ↗ | — | |
| 2025044 models | Model announcementReasoning View live pricing 200K tokensPricing ↗ | gpt-4.1Input$1.6Output$6.4/ 1M tokens 1M tokensPricing ↗ | |
| 2024071 models | — | — | gpt-4o-miniInput$0.0975Output$0.39/ 1M tokens 128K tokensPricing ↗ |
| 2024051 models | — | gpt-4oInput$2Output$8/ 1M tokens 128K tokensPricing ↗ | — |
Columns show positioning, rows show release months. Blank cells mean no listed model in that combination. Unknown dates are always placed last.
Model announcement dates are checked against OpenAI’s official news feed and link to the original article. Family announcements identify the family launch, not an individual variant’s API availability. Dates without an official source are labeled unverified. Missing dates are never inferred from model names or listing dates.
Classification reviewed
How the tiers work
Editorial selection tiers from Crazyrouter, not official OpenAI ratings. Compare within the same category and generation; a newer or more expensive model is not automatically a better fit.
Classification reviewed
Categories follow the output task: text covers chat, reasoning and code; images cover generation and editing; video covers video generation; embeddings cover vector retrieval; audio covers speech and music generation. Within images and video, quality and control guide the tiers; within embeddings, retrieval quality, vector size and serving cost do.
Flagship prioritizes capability, deep reasoning or output quality. It includes premium and highest-capability variants within a generation.
Mainstream balances capability, latency and cost for general production workloads. A standard variant can sit here even if another family has a stronger premium model.
Value prioritizes cost, latency or throughput, including smaller and efficiency-focused variants. Lower cost does not imply better quality on every task.
Coding and reasoning are specialties within text, not separate performance tiers. Image understanding alone does not make a text model an image-generation model.
Sol / Terra: positioning and official prices
OpenAI positions GPT-5.6 Sol as flagship and Terra as balanced. GPT-6.1 Terra costs less than Sol; OpenAI recommends Sol or Astra for the most complex coding tasks. In our three selection bands, Astra and Sol sit in flagship, Terra in mainstream, and Luna in value. Sharing a band does not imply equal capability: Astra remains the highest-capability option in GPT-6.
Official reference prices checked 2026-10-29 · USD per 1M text tokens · Standard, short context, uncached input. These are not Crazyrouter prices. GPT-5.6 Sol includes the current promotion, available at least through 2026-11-21. Long-context and faster processing rates differ.
| Model | Input | Output | selection tiers |
|---|---|---|---|
| GPT-6.1 Sol ↗ | $2 | $10 | Flagship |
| GPT-6.1 Terra ↗ | $1 | $5 | Mainstream |
| GPT-5.6 Sol ↗ | $4 | $20 | Flagship |
| GPT-5.6 Terra ↗ | $2 | $12 | Mainstream |
Guides and comparisons
NewsGPT-7 Outlook: What Do OpenAI’s 722 Mathematics Manuscripts Actually Tell Us?
Explore the GPT-7 speculation around 722 mathematics manuscripts: what the video claims, what Lean can verify, and what remains unknown about OpenAI’s unnamed model.
PricingGPT-5.5 Pricing Explained — OpenAI's Latest Flagship, Reasoning Tokens, and How to Save with Crazyrouter
Complete breakdown of GPT-5.5 API pricing — OpenAI's newest flagship model at $2.00/$8.00 per MTok, reasoning tokens, automatic caching, Batch API 50% off, and Crazyrouter savings.
NewsGPT-6 API Release Date: What Developers Should Watch Before OpenAI Ships It
Waiting for the GPT-6 API release date? Here is what developers should watch, what OpenAI has not confirmed publicly, and how to prepare before launch.
Podcast
AI Dev Tools: The Crazyrouter Podcast
Short episodes for developers on AI APIs, gateways, cost control and coding tools.
Latest episodes
EP196 · Oct 29, 2026 · 6:53
AI API Security Posture — Turn Controls Into Continuous Evidence
A practical guide to AI API security posture: inventory exposure, verify controls continuously, protect keys and data, constrain tools, and turn security assumptions into evidence that operators can act on.
EP195 · Oct 28, 2026 · 7:21
AI API Policy Drift — Detect When Production Rules Stop Matching Intent
A practical guide to policy drift in AI APIs: version routing and safety rules, detect stale enforcement, compare intended and observed behavior, and restore control before small gaps become incidents.
Questions & answers
- Which endpoint should I use?
- `/v1/chat/completions` for anything OpenAI-compatible; `/v1/responses` when you need reasoning items, encrypted reasoning or the Codex CLI. Both accept the same key, but endpoint support varies by model. GPT-6.1 Sol currently lists Chat Completions only.
- Is GPT-6 Astra available?
- Yes, at $3.25 / $16.25 per 1M tokens against OpenAI's $10 / $50. It is the most-routed model on the platform.
- Does Codex CLI work?
- Yes — set the provider base URL to `https://api.crazyrouter.com/v1` in `config.toml`; the one-click script on the Codex integration page does it for you.
- Are image models billed per token?
- GPT Image models are billed per image by size and quality, shown on each model page; text models are per token.
