Most Claude Opus 5.5 "regressions" are API changes, not a weaker model. Effort now defaults to medium (Opus 5 used high), thinking can't be turned off, text between tool calls arrives in thinking blocks that are empty by default, and forced tool choice returns a 400. Set effort explicitly, read blocks by type, re-run your golden set.
Updated 13 November 2026. On the OpenAI side, two "Sol" models exist and people mix them up: gpt-5.6-sol, the GPT-5.6 flagship, and gpt-6-sol, the cheaper tier below GPT-6 Astra, now followed by gpt-6.1-sol. Deadlines are forcing the move: OpenAI shuts down GPT-5.1, GPT-5.3-Codex and GPT-5.4-Nano in the API on 1 April 2027, the original GPT-5 and o3 on 11 December 2026, and Anthropic retires Claude Sonnet 4.5 on 30 November 2026. Don't just swap the model ID. Freeze a golden test set from real traffic, fix the breaking API changes, re-tune prompts and effort, shadow the new model on live traffic, then roll out behind a fallback. For most production apps that takes two to six weeks.
Model names, parameters, deadlines and prices in this playbook were re-checked on the Anthropic, OpenAI and Google model, deprecation and pricing pages on 13 November 2026. For token prices across every architecture, see our AI app development cost guide. For an eval plan that will satisfy an auditor, see LLM testing for regulated industries.
Mostly the API and its defaults changed. Anthropic lists four breaking changes and several behaviour differences from Opus 5, and each one can look like a quality drop if your code still assumes Opus 5 behaviour. Check these before you conclude the model got worse.
| What users report | Likely cause on Opus 5.5 | Fix |
|---|---|---|
| "Answers are shallower than Opus 5" | The default effort is medium; Opus 5 defaulted to high | Set output_config.effort explicitly and run an effort sweep |
| "The agent goes silent between tool calls" | Text between tool calls now arrives as thinking blocks, empty at the default display: "omitted" | Set thinking.display to "updates" (beta) or "summarized" and render non-empty thinking blocks |
| "Responses are cut off" or "costs went up" | Thinking is always on and counts against max_tokens; at the same effort the model also tends to think more per turn than Opus 5 | Raise max_tokens (start at 64k at xhigh or max), lower effort where quality holds |
| "My parser crashes" or "text is missing" | Responses can start with thinking blocks, so content[0].text is wrong | Select content blocks by type |
| "It refuses things Opus 5 did" | A biology classifier now runs alongside the cyber one, returning stop_reason: "refusal" | Handle refusals and configure fallback (see below) |
| "400 errors after the switch" | Disabled thinking, manual budgets, forced tool_choice, sampling parameters, prefill, old computer-use tool versions, or edited conversation history | See the parameter list in the next section |
There are real capability trade-offs too, and Anthropic is open about some of them. Its launch post (22 September 2026) shows GPT-6 Astra ahead on Terminal-Bench-Science (64.6% vs 58.7%), notes that safeguard interventions lowered some benchmark scores, and says "benchmark margins have become a less reliable guide to real-world differences." That is the argument for testing on your own cases rather than trusting either a launch chart or a forum thread.
Six request settings now return a 400 error on claude-opus-5-5: thinking disabled or with a manual budget, forced tool_choice, temperature/top_p/top_k, assistant prefill, and computer-use tool versions other than the new toolset. Effort is the only control for thinking depth. This list is from Anthropic's Opus 5.5 migration guide:
thinking field, or {"type": "adaptive"}, which is equivalent. {"type": "disabled"} and {"type": "enabled", "budget_tokens": N} are rejected.output_config.effort accepts low, medium, high, xhigh and max. The default is medium. The effort-2025-11-24 and interleaved-thinking-2025-05-14 beta headers are no longer needed.thinking.display defaults to "omitted". Use "summarized" for readable summaries or "updates" (beta header thinking-display-updates-2026-08-18) for progress updates only.auto (default) and none. any and a named tool are rejected, including on the token-counting endpoint. Use strict: true tools or structured outputs.temperature, top_p and top_k. Anthropic's deprecations page says API version 2026-10-21 removes them for every model; earlier API versions reject non-default values on Claude 4.7 and later.computer_toolset_20260801; computer_20251124 works only on Amazon Bedrock.inference_geo: "us" costs 1.1x. Fast mode is set with speed: "fast".Prompt caching also changed in your favour: cache reads are $0.20 per million tokens, and prompts of 512 tokens or more can be cached.
These are the API deadlines most likely to hit a production app in the next six months, as listed on the vendors' deprecation pages on 13 November 2026:
| Shutdown date | Vendor | What goes | Recommended replacement | Announced |
|---|---|---|---|---|
| 30 Nov 2026 (read-only since 31 Oct) | OpenAI | Evals platform (dashboard and API) | OpenAI recommends Promptfoo | 3 Jun 2026 |
| 30 Nov 2026 | OpenAI | Reusable prompts (v1/prompts) and Agent Builder | Prompts in your own code; Agents SDK or ChatGPT Workspace Agents | 3 Jun 2026 |
| 30 Nov 2026 | Anthropic | claude-sonnet-4-5-20250929 | claude-sonnet-5-5 | 30 Sep 2026 |
| 11 Dec 2026 | OpenAI | Original gpt-5 and o3 snapshots | gpt-5.6-sol | 11 Jun 2026 |
| 6 Jan 2027 | OpenAI | tts-1 | gpt-realtime-2.1-mini | 1 Oct 2026 |
| 1 Feb 2027 | OpenAI | gpt-5.5-cyber-preview | The most capable cyber model available to you | 5 Nov 2026 |
| 1 Apr 2027 | OpenAI | gpt-5.1, gpt-5.3-codex, gpt-5.4-nano | gpt-6-sol (Nano → gpt-6-luna) | 1 Oct 2026 |
| 7 May 2027 (earliest) | gemini-3.1-flash-lite | gemini-3.5-flash-lite | See Gemini deprecations page |
Keep three more dates on your radar. Claude Haiku 4.5 and Claude Opus 4.5 are still active, but Anthropic only commits to keeping them "not sooner than" 15 October and 24 November 2026, so a deprecation notice could arrive at any time; Anthropic promises at least 60 days' notice before retiring a publicly released model. Gemini 3.8 Flash doesn't retire, but its price doubles on 1 January 2027, to $1.50 input and $7.50 output per million tokens. And if your regression suite still lives in OpenAI's Evals platform, export it now: it is already read-only and shuts down on 30 November.

Sol is a tier name in OpenAI's model families, not a separate product. In GPT-5.6, Sol is the flagship (gpt-5.6-sol), with Terra and Luna below it. In GPT-6, the flagship is Astra, and Sol (gpt-6-sol, now gpt-6.1-sol) is the cheaper tier that OpenAI describes as near-Astra performance at lower cost.
| Model ID | Family role | Price per 1M tokens (input / output) | Reasoning effort levels |
|---|---|---|---|
gpt-6-astra | GPT-6 flagship, OpenAI's recommended default | $10 / $50 | low to max |
gpt-6.1-sol | Near-Astra performance at lower cost | $2 / $10 (cached input $0.10) | low to max, no none |
gpt-6-sol | Earlier GPT-6 Sol; replacement for GPT-5.1 and GPT-5.3-Codex | $2 / $10 (cached input $0.20) | none to max |
gpt-6-luna | Most efficient, high-volume | $0.10 / $0.50 | none to max |
gpt-5.6-sol | GPT-5.6 flagship; alias gpt-5.6 routes here | $4 / $20 listed (OpenAI shows promotional pricing until 30 Nov 2026) | none to max |
gpt-5.5 | Previous flagship, no shutdown date | $5 / $30 | none to xhigh |
All of these have a 1.05M-token context window (922K maximum input) and 128K maximum output on OpenAI's models pages. If you searched "Sol LLM" and meant a different open-source project with a similar name, this is not it.
Change the model to gpt-5.6-sol, keep your GPT-5.5 reasoning effort as the baseline and test one level lower, replace prompt_cache_retention with prompt_cache_options.ttl: "30m", and re-check brevity instructions, because GPT-5.6 is more concise by default. Then run your golden set before switching traffic.
gpt-5.6-sol, or the gpt-5.6 alias, which routes to Sol. Pin the full ID in production so an alias change can't surprise you.max and supports none through max. OpenAI's GPT-5.6 Sol prompting guide says to preserve your current GPT-5.5 effort as the baseline and compare one level lower, keep high or xhigh for cases where evals show a gain, and reserve max for the hardest quality-first work.text.verbosity instead.prompt_cache_retention with prompt_cache_options.ttl set to "30m", and review cache boundaries and cache-write billing.Before you commit, also price the jump straight to gpt-6.1-sol at $2 / $10. It skips one migration, but it requires the Responses API for tool calling and has no none effort, so it is a bigger code change. The next section covers it.
Both vendors made request settings that used to be harmless into hard errors. Changing the model string alone will fail in production. These are the changes their migration guides list (OpenAI's "Using GPT-6" and Anthropic's Opus 5.5 guide):
| Area | GPT-6 Sol / GPT-6.1 Sol / GPT-6 Luna | Claude Opus 5.5 |
|---|---|---|
| Sampling parameters | Remove temperature, top_p and top_logprobs when reasoning effort is not none (and logprobs on Chat Completions) | Omit temperature, top_p and top_k; API version 2026-10-21 rejects them with a 400 |
| Reasoning / thinking | Effort levels up to max, default medium. GPT-6.1 Sol and GPT-6 Astra have no none; use low. Replace minimal with low and compare | Adaptive thinking is always on. thinking: disabled and manual budgets are rejected. Effort is the only control, and its default is medium (Opus 5 defaulted to high) |
| Tool calling | GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Astra need the Responses API for tools. On Chat Completions, GPT-6 Sol and Luna call functions only at effort none | Forced tool choice (any or a named tool) is rejected. Use auto with strict tools or structured outputs |
| Response shape | Reasoning settings change output length and latency | Responses can start with thinking blocks, so code that reads content[0].text breaks. Thinking blocks must be passed back unmodified in tool loops |
| Prefill and caching | Replace prompt_cache_retention with prompt_cache_options.ttl set to "30m" | Assistant prefill is rejected; use structured outputs or system instructions |
| Safety and refusals | Check refusals on your own edge cases | stop_reason: "refusal" with a stop_details.category, now including "bio", with optional server-side fallback |
| Regional processing | Fast mode with EU data residency works on GPT-6.1 Sol and GPT-6 Luna, not on GPT-6 Sol or GPT-6 Astra | US-only inference costs 1.1x |
Two of these cause silent regressions rather than errors. On Opus 5.5, text that the model writes between tool calls now arrives in thinking blocks, which are empty by default, so an app that streamed those progress updates goes quiet and nothing throws an exception. And on GPT-6 Sol and Opus 5.5, an unset effort parameter means medium, which can change answer depth and latency without any code change.

Opus 5.5 runs a biology safety classifier in addition to the cybersecurity one, so it declines in more categories than Opus 5. A declined request returns HTTP 200 with stop_reason: "refusal" and a stop_details.category; handle it in code and retry on a fallback model instead of rewording the prompt until it gets through.
The categories in Anthropic's refusals and fallback guide are "cyber", "bio", "frontier_llm" (helping develop competing AI models), "reasoning_extraction" (asking the model to print its internal reasoning) and "general_harms", or null. Anthropic says benign work can trigger the cyber, bio, frontier_llm and general_harms classifiers. Anthropic does not publish an over-refusal rate comparing Opus 5.5 with Opus 5, so measure it on your own golden set.
stop_reason. A refusal can arrive before any output or mid-stream. Discard partial output in both cases.fallbacks: "default" with the server-side-fallback-2026-07-01 beta header and the API retries on the model Anthropic recommends for that category, in one call. Or name up to three fallback models, use the SDK middleware, or write your own retry. Server-side fallback is not available on the Batches API, and Haiku 5.5 has none.reasoning_extraction at the prompt. Prompts like "show your full chain of thought in the answer" get declined. Ask for a short explanation or the evidence instead, and set thinking.display: "summarized" if you need to see reasoning.bio, frontier_llm and reasoning_extraction categories, and every refusal counts against rate limits.No. A classifier refusal is a policy decision, not a bug, and prompt tricks that slip past it are the wrong fix. Anthropic bills some refusals specifically "to disrupt attempts to circumvent Anthropic's safeguards at scale," a workaround that works today can break with the next classifier update, and an app built on one fails unpredictably for your users.
When a legitimate request is refused, the durable fixes are the ones above: make the system prompt state the real use case and context clearly, route the refusal to a fallback model, move dual-use work into a verification program, and keep an eval set of your legitimate edge cases so you see when a model update changes the refusal rate. If a reworded legitimate request is still declined, Anthropic's guide says to contact support with the request ID.
List prices per million tokens (input / output) from the vendors' model and pricing pages on 13 November 2026. The per-1,000 columns reuse the assumptions from our cost guide: 6,000 input and 500 output tokens for a RAG answer, and 60,000 input and 3,000 output for an agent task. There is no caching, and reasoning tokens are not included.
| Migration | Price before → after | Per 1,000 RAG answers | Per 1,000 agent tasks | Watch out for |
|---|---|---|---|---|
| GPT-5.5 → GPT-5.6 Sol | $5 / $30 → $4 / $20 | $45.00 → $34.00 | $390 → $300 | Listed price; OpenAI shows promotional pricing until 30 Nov 2026 |
| GPT-5.5 → GPT-6.1 Sol | $5 / $30 → $2 / $10 | $45.00 → $17.00 | $390 → $150 | Responses API required for tools; no none effort |
| GPT-5.1 → GPT-6 Sol | $1.25 / $10 → $2 / $10 | $12.50 → $17.00 | $105 → $150 | Input costs 60% more. Cached input is $0.20 (Sol) or $0.10 (6.1 Sol) |
| GPT-5.3-Codex → GPT-6 Sol | $1.75 / $14 → $2 / $10 | $17.50 → $17.00 | $147 → $150 | Roughly flat. Output-heavy jobs get cheaper |
| GPT-5.4-Nano → GPT-6 Luna | $0.20 / $1.25 → $0.10 / $0.50 | $1.83 → $0.85 | $15.75 → $7.50 | About half the price. Check quality on your hardest cases |
| Claude Sonnet 4.5 → Sonnet 5.5 | $3 / $15 → $2 / $10 | $25.50 → ~$22.10 | $225 → ~$195 | The newer tokenizer uses roughly 1x to 1.35x as many tokens for the same text (we assume 1.3x), so savings are ~13%, not 33% |
| Claude Opus 5 → Opus 5.5 | $5 / $25 → $4 / $20 | $42.50 → $34.00 | $375 → $300 | Anthropic says Opus 5.5 costs 40% less than Opus 5 on typical workloads at default settings, partly from the lower default effort |
Three cost traps sit outside the list price. First, Anthropic bills thinking tokens as output tokens, and on Opus 5.5 every request thinks, because thinking can't be turned off. Check reasoning-token usage on the OpenAI side too. A workload that previously ran without thinking can produce more output tokens even at a lower price. Second, GPT-5.5, GPT-5.6 Sol, GPT-6 Sol and GPT-6.1 Sol charge 2x input and 1.5x output for the whole request above 272K input tokens, while Claude 4.6 and later models (except Haiku 5.5) charge the standard rate across the full 1M window. Third, batch processing costs half on both vendors, so move evals and back-office jobs there.
No vendor publishes latency guarantees for these models. Anthropic says Opus 5.5 generates output more than 30% faster than Opus 5, and its fast mode (up to 2.5x output speed) costs $8 / $40. OpenAI's GPT-6.1 Sol has no none effort level, which puts a floor under its response time. Measure p50 and p95 latency on your own prompts at the effort you plan to ship. Don't trust a launch chart.
Newer models are better on average and worse on some of your cases. The usual causes are:
reasoning_extraction refusal.Without an eval set, you find these through customer complaints. Avoiding that is the whole point of the next section.
Six steps, in this order. Two to six weeks is realistic for one production feature, depending mainly on whether you already have evals.

Use one row per risk and set the threshold before you see the results. The thresholds below are examples. Set your own from your baseline.
| Test | What it measures | Example pass rule |
|---|---|---|
| Task accuracy | Correct answer or action on the golden set, scored by rules, human labels or a calibrated LLM grader | No worse than baseline minus 1 point overall, and no drop on any critical intent |
| Format validity | JSON or schema parses, required fields present | 100% on structured outputs |
| Tool-call correctness | Right tool, valid arguments, no forbidden calls, call count per task | Zero forbidden calls; median call count within 20% of baseline |
| Refusals | Over-refusal on legitimate requests (by stop_details.category), under-refusal on red-team prompts | No new refusals on the golden set; all red-team cases blocked |
| Grounding | Answers supported by retrieved sources, with citations that resolve | No unsupported claims on the regulated-content subset |
| Latency | p50 and p95 end to end, including tools | p95 under your product timeout with margin |
| Cost | Tokens and dollars per task, including reasoning tokens | Within the re-forecast budget |
If your industry is regulated, keep the run results, model versions and thresholds as evidence. A model change is exactly the kind of event auditors ask about. Our regulated-industry eval plan maps these tests to HIPAA, PCI DSS and the EU AI Act, and AI agent evaluation and observability covers the tooling.
Switch models through config, route by task, test the fallback path, and watch online metrics for two weeks after cutover. Five practices make that work:
Fifteen checks, from inventory and golden set to refusal handling, rollback and re-forecast cost. Tick every one before you move 100% of traffic:
thinking.display is set if your UI shows progress between tool calls.max_tokens is re-budgeted for thinking plus answer.stop_reason: "refusal" is handled, with a tested fallback path.On 1 April 2027. OpenAI announced on 1 October 2026 that gpt-5.1, gpt-5.3-codex and gpt-5.4-nano will be shut down that day, with gpt-6-sol as the replacement for the first two and gpt-6-luna for Nano. Requests to a shut-down model fail.
Not as of 13 November 2026. OpenAI's deprecations page lists no shutdown date for gpt-5.5, which is priced at $5 input and $30 output per million tokens. Only gpt-5.5-cyber-preview is scheduled to shut down, on 1 February 2027. Changes to which models appear in ChatGPT are separate from API deprecations.
Both exist. gpt-5.6-sol is the flagship of the GPT-5.6 family and the replacement OpenAI names for the original GPT-5 and o3. gpt-6-sol is the lower-cost tier of GPT-6, below GPT-6 Astra, and the replacement for GPT-5.1 and GPT-5.3-Codex. gpt-6.1-sol is its newer version.
Run both on your golden set and decide on the evidence. GPT-6.1 Sol costs $2 / $10 with a 1.05M context. Opus 5.5 costs $4 / $20 with a 1M context and always-on thinking. GPT-6 Astra ($10 / $50) is the comparison for the hardest work. Price per token matters less than cost per successful task, and that depends on your prompts, tools and effort level.
No. Benchmarks average over tasks that aren't yours, and Anthropic itself notes that benchmark margins have become a less reliable guide to real-world differences. A 200-case golden set takes days to build and is the only way to know whether your app got better or worse.
Changing the model ID takes minutes. A safe migration of one production feature typically takes two to six weeks. Most of that is building the eval set, tuning prompts and effort, and running shadow traffic long enough to trust the numbers.
A migration is a well-bounded piece of work: inventory, evals, code changes and rollout. That makes it suitable for a fixed price. Our AI agent development work is priced by phase from $10K, with a working demo every Friday and full code ownership from day one; our pricing page explains how phases are scoped. Our open-source agent framework, Kite, ships prompt A/B testing with statistical confidence intervals on real traffic. It exists because "the new prompt feels better" is not a release criterion. If you're unsure whether your agent should be rebuilt rather than migrated, our framework guide and agent cost guide are good places to start.
BeevR is a senior, founder-led AI studio in Hanoi, Vietnam. If you have a model deadline coming up, book a 30-minute call and tell us which models you run. We'll map the breaking changes and the eval work before you commit to anything.