Model guides
Model ids, context windows, pricing and availability — check what is actually callable before you build on it.
Claude Haiku 5.5 complete guide
Two price tiers ($0.10 / $0.50 up to 100K, $0.50 / $2.50 above), 1M / 128K, platform IDs and how it differs from Haiku 4.5.
Updated 2026-10-10
gpt-5.3-codex, gpt-5.1, gpt-5.4-nano shut down 2027-04-01
Which model replaces each of the three, how to handle snapshots and default effort, and what changes in Codex (official table checked 2026-10-08)
Updated 2026-10-08
GPT-6 Astra complete guide
Shipped 2026-09-03. Specs, pricing, four migration constraints, and three things OpenAI still has not published.
Updated 2026-10-08
GPT-6 Astra quota consumption
Official credits table: Astra is exactly 2.5× GPT-5.6 Sol. Per-plan message allowances and three ways to burn less.
Updated 2026-10-08
Migrating to GPT-6 Astra
The four hard constraints in the official migration guide, and the one that gets mistaken for a bug.
Updated 2026-10-08
GPT-5.6 Release Date: July 9, 2026 – Now Succeeded by GPT-6
GPT-5.6 release date: July 9, 2026. As of 2026-10-07 OpenAI has since shipped GPT-6 Astra (Sep 3), GPT-6 Sol and Luna (Sep 22) and GPT-6.1 Sol (Sep 29).
Updated 2026-10-08
Claude Sonnet 5 API: Setup Guide, Model ID & Effort Parameter
How to use the Claude Sonnet 5 API: model id claude-sonnet-5, curl and Python SDK examples, adaptive thinking, the effort parameter, re-tuning max_tokens for the new tokenizer, and stable access through QCode.
Updated 2026-10-08
Claude Sonnet 5.5 complete guide
Released 2026-09-28: 1M / 128K, $2 / $10, cache reads $0.10 since 2026-10-07, plus default effort and the five breaking changes.
Updated 2026-10-08
Claude Opus 5 Complete Guide — Same Price and Window as Opus 4.8 (Opus 5.5 newest since 2026-09-22) | QCode.cc
Claude Opus 5 is live at $5/$25 per million tokens with 1M context and a 512-token cache floor. As of 2026-09-29 Anthropic's newest Opus is Opus 5.5 ($4/$20), released 2026-09-22.
Updated 2026-10-08
Claude adaptive thinking and effort, model by model
Which models cannot turn thinking off, the five effort levels and their defaults, where budget_tokens stands, and Claude Code settings. Checked 2026-10-08.
Updated 2026-10-08
GPT-6.1 Sol API guide
Released 2026-09-29: $2 / $10, cached input $0.10, 1.05M context, full-request pricing above 272K, compared line by line with gpt-6-sol.
Updated 2026-10-07
Is Claude Sonnet 5 Available? Yes, as Legacy (Oct 2026)
As of Oct 8, 2026, Claude Sonnet 5 (claude-sonnet-5) is still available as a legacy model, retiring no sooner than June 30, 2027. Sonnet 5.5 is now current.
Updated 2026-10-07
Claude Sonnet 5: Model ID, Context Window, Pricing & Review (2026)
Claude Sonnet 5 (claude-sonnet-5), released 2026-06-30: 1M context, 128K output, $2/$10. As of 2026-10-08 it is Legacy yet available; Sonnet 5.5 is current.
Updated 2026-10-07
Claude Opus 5.5 complete guide
Claude Opus 5.5 guide: pricing, caching, the comparison with Opus 5, calling it on QCode
Updated 2026-09-29
DeepSeek V4 Pro 0813 Guide
1.6T-class GA, agent benchmarks, peak/off-peak pricing, QCode catalog price
Updated 2026-09-21
DeepSeek V4.1 Flash released guide
Official 2026-09-10 release: new id, 1M/384K, peak/off-peak pricing, routing conflict, and which id to use on QCode.
Updated 2026-09-21
Claude Opus 4.7 Complete Guide — Coding / Vision / Agentic Leap | QCode.cc
Claude Opus 4.7 complete guide: 64.3% on SWE-bench Pro, 3x vision resolution, new xhigh effort tier, native 1M context. Same price as 4.6 ($5/$25). Covers coding breakthroughs, vision upgrades, migration guide, and official benchmarks.
Updated 2026-09-21
Claude compaction: the two beta paths
Headers, block placement, the 400 and the billing wording for both paths (official docs captured 2026-09-21)
Updated 2026-09-21
Qwen3.8-Max guide
2.4T MoE, $2/$6, open weights; on QCode (catalogue checked 2026-09-20)
Updated 2026-09-20
The Complete Guide to Qwen3.7-Plus
On sale alongside Max, real usage data verified
Updated 2026-09-20
Qwen3.8-Flash status tracker
Released 2026-08-26 and its public list price; qwen3.8-flash is in our catalog and usage table (checked 2026-09-18)
Updated 2026-09-19
The Complete Guide to Claude Opus 4.6
SWE-bench score, pricing, and how to use it
Updated 2026-09-19
The Complete Guide to Claude Haiku 4.5
Pricing, positioning, and real call-volume data on QCode
Updated 2026-09-19
GLM-5.3-Flash complete guide
320B-A18B, 1M context, MIT weights; promo ends 9/9; real DeepSWE 63.4%
Updated 2026-09-09
Claude Fable 5.1 complete guide
Cache reads 75% cheaper, input and output unchanged, 1M context, and how to decide whether to switch from Fable 5.
Updated 2026-09-02
GLM-5.2: 2026's Strongest Open-Weight Coding Model — Benchmarks and Access
GLM-5.2 is 2026's strongest open-weight coding model (MIT, 1M context). Verified benchmarks, pricing, supply and compliance caveats, and what you can use today.
Updated 2026-08-17
Claude Opus 4.8 Complete Guide — Sharper Agentic Judgement, 4x Fewer Code Flaws | QCode.cc
Claude Opus 4.8 complete guide: sharper agentic judgement, 4x fewer code flaws than 4.7, Online-Mind2Web 84%, native 1M context. Same price as 4.7 ($5/$25). Covers agentic coding gains, capability upgrades, migration guide, and official benchmarks.
Updated 2026-08-17
Claude Fable 5 Complete Guide — A New Flagship Tier Above Opus | QCode.cc
Claude Fable 5 guide: Anthropic's most capable tier above Opus — 1M context, 128K output, $10/$50. Available on the API and live on QCode; tiered by plan on Anthropic subscriptions since 2026-07-19.
Updated 2026-08-17
Is Claude Fable 5 Available? API Yes, Subscriptions Tiered by Plan (July 2026) | QCode.cc
Fable 5 is available on the API throughout. On Anthropic's own subscriptions it has been tiered by plan since July 19, 2026: standard on Max and Team/Enterprise premium seats, pay-as-you-go usage credits on Pro and standard Team seats.
Updated 2026-08-17
Kimi K3 guide
kimi-k3: 2.8T, 1M, $3/$0.30/$15, thinking will not turn off
Updated 2026-08-16