netcracker/ai-for-dummies
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(15d): complete localization of full-guide page to PT

Browse Source
This commit is contained in:
Marcos Paulo
2026-09-05 22:30:50 +00:00
parent c022a93302
commit 054393f7af
38 changed files with 1322 additions and 325 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/references/model-routing.md
+62 -20
View File
@@ -1,25 +1,42 @@
# Model routing and reasoning controls
Verified against first-party documentation on 2026-09-02. Model catalogs and aliases change; pin production model IDs and re-check the linked compatibility tables before rollout.
Verified against first-party documentation on 2026-09-02. Model catalogs and
aliases change; pin production model IDs and re-check the linked compatibility
tables before rollout.
## Two independent routing knobs
1. **Model tier** chooses the capability, latency, and cost envelope.
2. **Effort / thinking control** changes how much reasoning work a supported model performs for one request.
2. **Effort / thinking control** changes how much reasoning work a supported
model performs for one request.
Do not assume that every effort value works with every model or product. Unsupported values may fail, be ignored, or be mapped to another level depending on the client.
Do not assume that every effort value works with every model or product.
Unsupported values may fail, be ignored, or be mapped to another level depending
on the client.
## OpenAI
The current GPT-5.6 family exposes the **Sol**, **Terra**, and **Luna** model tiers. Its documented `reasoning.effort` values are `none`, `low`, `medium`, `high`, `xhigh`, and `max`. Availability remains model-specific, so select from the levels shown for the chosen model rather than treating the full list as universal. [OpenAI: latest model guide](https://developers.openai.com/api/docs/guides/latest-model)
The current GPT-5.6 family exposes the **Sol**, **Terra**, and **Luna** model
tiers. Its documented `reasoning.effort` values are `none`, `low`, `medium`,
`high`, `xhigh`, and `max`. Availability remains model-specific, so select from
the levels shown for the chosen model rather than treating the full list as
universal.
[OpenAI: latest model guide](https://developers.openai.com/api/docs/guides/latest-model)
Use a lower-cost tier and low effort for bounded, mechanical work; raise the model tier or effort for planning, architecture, difficult debugging, and final review. This is routing guidance, not an API guarantee.
Use a lower-cost tier and low effort for bounded, mechanical work; raise the
model tier or effort for planning, architecture, difficult debugging, and final
review. This is routing guidance, not an API guarantee.
## Anthropic Claude
### Model tier
Claude Code provides the aliases `opus`, `sonnet`, and `haiku`: Opus is intended for complex reasoning, Sonnet for everyday coding, and Haiku for simple, fast work. Aliases resolve to provider-dependent recommended versions and can change over time; use a full model ID when reproducibility matters. Claude Code also documents `opusplan`, which uses Opus in plan mode and Sonnet for execution. [Claude Code: model configuration](https://docs.anthropic.com/en/docs/claude-code/model-config)
Claude Code provides the aliases `opus`, `sonnet`, and `haiku`: Opus is intended
for complex reasoning, Sonnet for everyday coding, and Haiku for simple, fast
work. Aliases resolve to provider-dependent recommended versions and can change
over time; use a full model ID when reproducibility matters. Claude Code also
documents `opusplan`, which uses Opus in plan mode and Sonnet for execution.
[Claude Code: model configuration](https://docs.anthropic.com/en/docs/claude-code/model-config)
Copy-ready Claude Code switches:
@@ -37,7 +54,12 @@ claude --model opus
### Effort
The Claude API parameter is `output_config.effort`. The documented levels are `low`, `medium`, `high`, `xhigh`, and `max`; `high` is the API default. `xhigh` and `max` have narrower model support, and Haiku 4.5 does not support effort. Effort affects the whole response—including thinking and tool calls—and is a behavioral signal, not a strict token budget. [Anthropic: effort](https://docs.anthropic.com/en/docs/build-with-claude/effort)
The Claude API parameter is `output_config.effort`. The documented levels are
`low`, `medium`, `high`, `xhigh`, and `max`; `high` is the API default. `xhigh`
and `max` have narrower model support, and Haiku 4.5 does not support effort.
Effort affects the whole response—including thinking and tool calls—and is a
behavioral signal, not a strict token budget.
[Anthropic: effort](https://docs.anthropic.com/en/docs/build-with-claude/effort)
Documented Python example:
@@ -53,27 +75,45 @@ response = client.messages.create(
)
```
Claude Code exposes `/effort`; its available choices depend on the active model. Current Claude Code documentation lists `low`, `medium`, `high`, `xhigh`, and `max` for supported Opus versions, while some Opus/Sonnet versions omit `xhigh`. When a selected level is unsupported, Claude Code can fall back to the highest supported level at or below it. [Claude Code: effort compatibility](https://docs.anthropic.com/en/docs/claude-code/model-config#adjust-effort-level)
Claude Code exposes `/effort`; its available choices depend on the active model.
Current Claude Code documentation lists `low`, `medium`, `high`, `xhigh`, and
`max` for supported Opus versions, while some Opus/Sonnet versions omit `xhigh`.
When a selected level is unsupported, Claude Code can fall back to the highest
supported level at or below it.
[Claude Code: effort compatibility](https://docs.anthropic.com/en/docs/claude-code/model-config#adjust-effort-level)
## Google Gemini
### Model tier
Gemini uses model families rather than interchangeable aliases: **Pro** targets the most complex reasoning, **Flash** balances capability and throughput, and **Flash-Lite** prioritizes latency, volume, and cost. Select an explicit endpoint such as `gemini-3.7-flash`; Google recommends stable model names for most production applications because `latest` aliases can be hot-swapped. [Gemini API: models](https://ai.google.dev/gemini-api/docs/models)
Gemini uses model families rather than interchangeable aliases: **Pro** targets
the most complex reasoning, **Flash** balances capability and throughput, and
**Flash-Lite** prioritizes latency, volume, and cost. Select an explicit
endpoint such as `gemini-3.7-flash`; Google recommends stable model names for
most production applications because `latest` aliases can be hot-swapped.
[Gemini API: models](https://ai.google.dev/gemini-api/docs/models)
### Thinking level
For Gemini 3 models, the control is `thinkingLevel` in SDKs (`thinking_level` in Python). Across the family the documented values are `minimal`, `low`, `medium`, and `high`, but support and defaults vary by model. For example, Gemini 3.7 Flash supports `low`, `medium`, and `high` and defaults to `medium`; Gemini 3.1 Pro supports `low`, `medium`, and `high` and defaults to `high`. `minimal` is unavailable on several models and does not guarantee that reasoning is completely off where supported. Gemini 2.5 uses `thinkingBudget`, not `thinkingLevel`. [Gemini API: thinking](https://ai.google.dev/gemini-api/docs/thinking)
For Gemini 3 models, the control is `thinkingLevel` in SDKs (`thinking_level` in
Python). Across the family the documented values are `minimal`, `low`, `medium`,
and `high`, but support and defaults vary by model. For example, Gemini 3.7
Flash supports `low`, `medium`, and `high` and defaults to `medium`; Gemini 3.1
Pro supports `low`, `medium`, and `high` and defaults to `high`. `minimal` is
unavailable on several models and does not guarantee that reasoning is
completely off where supported. Gemini 2.5 uses `thinkingBudget`, not
`thinkingLevel`.
[Gemini API: thinking](https://ai.google.dev/gemini-api/docs/thinking)
Documented JavaScript pattern:
```javascript
import { GoogleGenAI, ThinkingLevel } from "@google/genai";
import { GoogleGenAI, ThinkingLevel } from '@google/genai';
const ai = new GoogleGenAI({});
const response = await ai.models.generateContent({
model: "gemini-3.7-flash",
contents: "Review this implementation plan.",
model: 'gemini-3.7-flash',
contents: 'Review this implementation plan.',
config: {
thinkingConfig: {
thinkingLevel: ThinkingLevel.LOW,
@@ -86,11 +126,13 @@ console.log(response.text);
## Practical routing baseline
| Work | Model tier | Effort / thinking |
| --- | --- | --- |
| Formatting, lookup, narrow edit | Haiku / Flash-Lite / Luna | Low or minimal where supported |
| Normal implementation, tests, review | Sonnet / Flash / Terra | Medium |
| Architecture, orchestration, hard debugging | Opus / Pro / Sol | High |
| Frontier or long-horizon work with measured benefit | Strongest supported tier | `xhigh` or `max` only where documented |
| Work | Model tier | Effort / thinking |
| --------------------------------------------------- | ------------------------- | -------------------------------------- |
| Formatting, lookup, narrow edit | Haiku / Flash-Lite / Luna | Low or minimal where supported |
| Normal implementation, tests, review | Sonnet / Flash / Terra | Medium |
| Architecture, orchestration, hard debugging | Opus / Pro / Sol | High |
| Frontier or long-horizon work with measured benefit | Strongest supported tier | `xhigh` or `max` only where documented |
Treat this table as a starting hypothesis. Evaluate quality, latency, and cost on representative tasks, then route to the cheapest combination that still passes the required checks.
Treat this table as a starting hypothesis. Evaluate quality, latency, and cost
on representative tasks, then route to the cheapest combination that still
passes the required checks.