@cartanova/qgrid-ai-sdk 2.9.7 → 2.9.10
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.ko.md +6 -1
- package/README.md +7 -2
- package/dist/index.d.ts +1 -1
- package/package.json +1 -1
package/README.ko.md
CHANGED
|
@@ -368,6 +368,7 @@ AI SDK response metadata로 실제 serving 모델을 다르게 보고하면 step
|
|
|
368
368
|
type QgridSupportedModel =
|
|
369
369
|
// OpenAI (direct private Codex Responses backend)
|
|
370
370
|
| "openai/gpt-6-astra"
|
|
371
|
+
| "openai/gpt-6.1-sol"
|
|
371
372
|
| "openai/gpt-6-sol"
|
|
372
373
|
| "openai/gpt-6-luna"
|
|
373
374
|
| "openai/gpt-5.6-sol"
|
|
@@ -396,6 +397,7 @@ type QgridSupportedModel =
|
|
|
396
397
|
| "anthropic/claude-opus-4-8"
|
|
397
398
|
| "anthropic/claude-opus-5"
|
|
398
399
|
| "anthropic/claude-opus-5-5"
|
|
400
|
+
| "anthropic/claude-sonnet-5-5"
|
|
399
401
|
```
|
|
400
402
|
|
|
401
403
|
`openai/gpt-5.4`, `openai/gpt-5.4-mini`, `openai/gpt-5.2`, `openai/gpt-5.3-codex`는 하위 호환을 위해 타입에 남아 있지만, qgrid가 사용하는 ChatGPT 구독 Codex 경로에서는 더 이상 제공되지 않습니다. `gpt-5.4`와 `gpt-5.4-mini`는 2026-08-31에 retire되었고(대체: `openai/gpt-5.6-terra`, `openai/gpt-5.6-luna`), `gpt-5.2`와 `gpt-5.3-codex`는 그보다 먼저 해당 경로에서 제거되었습니다. 이 id로 요청하면 백엔드에서 실패합니다.
|
|
@@ -405,10 +407,11 @@ type QgridSupportedModel =
|
|
|
405
407
|
| 모델 | Context (Codex 카탈로그) | 최대 출력 (공개 API) | 1M tokens당 input / cached input / cache write / output |
|
|
406
408
|
|---|---:|---:|---:|
|
|
407
409
|
| `openai/gpt-6-astra` | 272K | 128K | $10 / $1 / $12.50 / $50 |
|
|
410
|
+
| `openai/gpt-6.1-sol` | 272K | 128K | $2 / $0.10 / $2.50 / $10 |
|
|
408
411
|
| `openai/gpt-6-sol` | 272K | 128K | $2 / $0.20 / $2.50 / $10 |
|
|
409
412
|
| `openai/gpt-6-luna` | 272K | 128K | $0.10 / $0.01 / $0.125 / $0.50 |
|
|
410
413
|
|
|
411
|
-
2026-09-23에 조회한 Codex 카탈로그는
|
|
414
|
+
2026-09-23에 조회한 Codex 카탈로그는 Astra, Sol, Luna 모두 272K context window를 제공합니다. Astra와 Sol은 `ultra`까지, Luna는 `max`까지 reasoning effort를 지원합니다. 백엔드 기본값은 세 모델 모두 `medium`이며, qgrid SDK의 기본값은 기존대로 `low`이니 다른 깊이가 필요하면 effort를 명시하세요. [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna)의 공개 API 문서는 별도로 1.05M context, 최대 입력 922K, 최대 출력 128K와 `max`까지의 effort를 명시하며 `ultra`는 포함하지 않습니다. 이 공개 API 한도를 구독 경로의 한도로 간주하지 않습니다. Qgrid 비용 추정에는 [표준 API 단가](https://developers.openai.com/api/docs/pricing)를 사용합니다. Cache write는 uncached input 단가의 1.25x이며, 입력이 272K tokens를 넘으면 요청 전체에 input/cache 2x, output 1.5x 단가가 적용됩니다. GPT-6 Sol과 Luna(2026-09-22 출시)는 GPT-5.6 Sol/Luna의 절반 단가이며, 기존 모델 단가는 2026-09-23에 재확인했고 변동이 없습니다. [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol)(2026-09-29 출시)은 GPT-6 Sol과 단가가 같고 cached input만 $0.10입니다. 2026-09-30에 조회한 Codex 카탈로그는 272K context window, `ultra`까지의 effort, 백엔드 기본값 `low`를 명시하며, 같은 날 qgrid 요청 형태로 라이브 생성에 성공했습니다. `openai/gpt-5.5`는 2026-10-14에 Codex/ChatGPT 경로에서 은퇴하므로 `openai/gpt-6.1-sol` 또는 `openai/gpt-6-luna`로 옮기세요.
|
|
412
415
|
|
|
413
416
|
### GPT-5.6 사양
|
|
414
417
|
|
|
@@ -430,6 +433,8 @@ Qgrid 비용 추정에는 [표준 API 단가](https://developers.openai.com/api/
|
|
|
430
433
|
|
|
431
434
|
`anthropic/claude-opus-5-5`(2026-09-22 출시)는 1M context와 128K 최대 출력을 지원합니다. 1M tokens당 단가는 input $4, cache read $0.20(input의 0.05x), 5분 cache write $5, 1시간 cache write $8, output $20입니다. adaptive thinking이 항상 켜져 있고 끌 수 없으므로 qgrid는 Fable과 같이 이를 보존하고 `effort`로 추론 깊이를 조절합니다. Opus 5.5의 API 수준 파괴적 변경(forced `tool_choice` 거부, 모델에 귀속된 thinking 블록)은 Fable 5.1과 같은 이유로 qgrid에 영향을 주지 않습니다. Opus 5 단가는 변동이 없습니다.
|
|
432
435
|
|
|
436
|
+
`anthropic/claude-sonnet-5-5`(2026-09-29 출시)는 1M context와 128K 최대 출력을 지원하며 Sonnet 5와 같은 단가입니다. 1M tokens당 input $2, cache read $0.20, 5분 cache write $2.50, 1시간 cache write $4, output $10입니다. thinking 비활성화를 거부하므로 qgrid는 Opus 5.5와 같이 adaptive thinking을 유지하고 `effort`로 추론 깊이를 조절합니다.
|
|
437
|
+
|
|
433
438
|
Claude Code는 Fable의 safety refusal을 다른 Opus 모델로 자동 재시도할 수 있습니다. 현재 CLI는 refusal 카테고리에 따라 Opus 5 또는 Opus 4.8을 고릅니다. 이 경우 AI SDK 응답의 `response.modelId`와 `providerMetadata.qgrid.model`은 실제 serving 모델인 Opus를 가리킵니다. `providerMetadata.qgrid.requestedModel`은 Fable로 유지되고, `providerMetadata.qgrid.modelFallbacks`에 refusal fallback 이력이 담깁니다. 같은 metadata에서 `costSource`와 5분/1시간 cache-write 토큰 분해도 확인할 수 있습니다.
|
|
434
439
|
|
|
435
440
|
`openai/gpt-5.3-codex-spark`는 아직 token 단가가 확정·공개되지 않은 research preview입니다. 따라서 qgrid는 generic fallback 추정치를 보고하며, 이를 공식 단가로 취급하지 않습니다.
|
package/README.md
CHANGED
|
@@ -314,7 +314,7 @@ import { generateText } from "ai";
|
|
|
314
314
|
import { qgrid, type QgridProviderOptions } from "@cartanova/qgrid-ai-sdk";
|
|
315
315
|
|
|
316
316
|
const result = await generateText({
|
|
317
|
-
model: qgrid("openai/gpt-
|
|
317
|
+
model: qgrid("openai/gpt-6.1-sol", { projectName: "deti" }),
|
|
318
318
|
prompt: "An isolated character. Everything outside the character must be transparent, with no backdrop or checkerboard.",
|
|
319
319
|
providerOptions: {
|
|
320
320
|
qgrid: {
|
|
@@ -404,6 +404,7 @@ The `qgrid()` provider has its own lifecycle, so the logger automatically suppre
|
|
|
404
404
|
type QgridSupportedModel =
|
|
405
405
|
// OpenAI (direct private Codex Responses backend)
|
|
406
406
|
| "openai/gpt-6-astra"
|
|
407
|
+
| "openai/gpt-6.1-sol"
|
|
407
408
|
| "openai/gpt-6-sol"
|
|
408
409
|
| "openai/gpt-6-luna"
|
|
409
410
|
| "openai/gpt-5.6-sol"
|
|
@@ -432,6 +433,7 @@ type QgridSupportedModel =
|
|
|
432
433
|
| "anthropic/claude-opus-4-8"
|
|
433
434
|
| "anthropic/claude-opus-5"
|
|
434
435
|
| "anthropic/claude-opus-5-5"
|
|
436
|
+
| "anthropic/claude-sonnet-5-5"
|
|
435
437
|
```
|
|
436
438
|
|
|
437
439
|
`openai/gpt-5.4`, `openai/gpt-5.4-mini`, `openai/gpt-5.2`, and `openai/gpt-5.3-codex` remain in the type for backward compatibility, but the ChatGPT-subscription Codex route that qgrid uses no longer serves them. `gpt-5.4` and `gpt-5.4-mini` retired on 2026-08-31 (replacements: `openai/gpt-5.6-terra` and `openai/gpt-5.6-luna`); `gpt-5.2` and `gpt-5.3-codex` were removed from that route earlier. Requests for these ids fail at the backend.
|
|
@@ -441,10 +443,11 @@ type QgridSupportedModel =
|
|
|
441
443
|
| Model | Context (Codex catalog) | Max output (public API) | Input / cached input / cache write / output per 1M tokens |
|
|
442
444
|
|---|---:|---:|---:|
|
|
443
445
|
| `openai/gpt-6-astra` | 272K | 128K | $10 / $1 / $12.50 / $50 |
|
|
446
|
+
| `openai/gpt-6.1-sol` | 272K | 128K | $2 / $0.10 / $2.50 / $10 |
|
|
444
447
|
| `openai/gpt-6-sol` | 272K | 128K | $2 / $0.20 / $2.50 / $10 |
|
|
445
448
|
| `openai/gpt-6-luna` | 272K | 128K | $0.10 / $0.01 / $0.125 / $0.50 |
|
|
446
449
|
|
|
447
|
-
The Codex catalog fetched on 2026-09-23 advertises a 272K context window for
|
|
450
|
+
The Codex catalog fetched on 2026-09-23 advertises a 272K context window for Astra, Sol, and Luna. Astra and Sol support reasoning effort through `ultra`; Luna supports it through `max`. The backend default is `medium` for all three, while qgrid's SDK defaults to `low`; select an effort explicitly to override it. The public API model pages for [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), and [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) separately list a 1.05M context window, 922K maximum input, 128K maximum output, and reasoning effort through `max` (no `ultra`). Those public limits do not establish the subscription route's limits. [Standard API pricing](https://developers.openai.com/api/docs/pricing) is used for qgrid's cost estimate: cache writes cost 1.25x the uncached input rate, and input over 272K tokens applies 2x input/cache and 1.5x output rates to the full request. GPT-6 Sol and Luna (released 2026-09-22) are priced at half of GPT-5.6 Sol and Luna; existing model prices were re-verified on 2026-09-23 and did not change. [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) (released 2026-09-29) keeps GPT-6 Sol's prices except cached input at $0.10; the Codex catalog fetched on 2026-09-30 lists a 272K context window, effort through `ultra`, and a `low` backend default, and a live generation through qgrid's request shape succeeded the same day. `openai/gpt-5.5` retires from the Codex/ChatGPT route on 2026-10-14; migrate to `openai/gpt-6.1-sol` or `openai/gpt-6-luna`.
|
|
448
451
|
|
|
449
452
|
### GPT-5.6 specifications
|
|
450
453
|
|
|
@@ -466,6 +469,8 @@ Qgrid uses [Standard API pricing](https://developers.openai.com/api/docs/pricing
|
|
|
466
469
|
|
|
467
470
|
`anthropic/claude-opus-5-5` (released 2026-09-22) has a 1M context window and 128K max output. Its prices per 1M tokens are $4 input, $0.20 cache read (0.05x the input price), $5 five-minute cache write, $8 one-hour cache write, and $20 output. Adaptive thinking is always on and cannot be disabled, so qgrid preserves it and uses `effort` to control depth, as it does for Fable. Opus 5.5's API-level breaking changes (forced `tool_choice` rejection, model-bound thinking blocks) do not affect qgrid for the same reason as Fable 5.1. Opus 5 pricing did not change.
|
|
468
471
|
|
|
472
|
+
`anthropic/claude-sonnet-5-5` (released 2026-09-29) has a 1M context window and 128K max output at Sonnet 5's prices: $2 input, $0.20 cache read, $2.50 five-minute cache write, $4 one-hour cache write, and $10 output per 1M tokens. It rejects disabled thinking, so qgrid keeps adaptive thinking on and uses `effort` to control depth, as it does for Opus 5.5.
|
|
473
|
+
|
|
469
474
|
Claude Code may automatically retry a Fable safety refusal on another Opus model; the current CLI picks Opus 5 or Opus 4.8 by refusal category. In that case, the AI SDK response's `response.modelId` and `providerMetadata.qgrid.model` identify Opus as the actual serving model. `providerMetadata.qgrid.requestedModel` remains Fable, and `providerMetadata.qgrid.modelFallbacks` contains the refusal fallback history. The metadata also exposes `costSource` and the 5m/1h cache-write token split.
|
|
470
475
|
|
|
471
476
|
`openai/gpt-5.3-codex-spark` remains a research preview without final published per-token rates. qgrid therefore reports its generic fallback estimate rather than presenting that estimate as official pricing.
|
package/dist/index.d.ts
CHANGED
|
@@ -96,7 +96,7 @@ type QgridAnthropicProviderOptions = QgridCommonProviderOptions & {
|
|
|
96
96
|
* `QgridOpenAIProviderOptions` / `QgridAnthropicProviderOptions` 를 직접 쓰는 편이 정확하다.
|
|
97
97
|
*/
|
|
98
98
|
type QgridProviderOptions = QgridOpenAIProviderOptions | QgridAnthropicProviderOptions;
|
|
99
|
-
type QgridSupportedModel = "openai/gpt-6-astra" | "openai/gpt-6-sol" | "openai/gpt-6-luna" | "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/gpt-5.6-luna" | "openai/gpt-5.5" | "openai/gpt-5.4" | "openai/gpt-5.2" | "openai/gpt-5.4-mini" | "openai/gpt-5.3-codex" | "openai/gpt-5.3-codex-spark" | "anthropic/claude-fable-5-1" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-4-7" | "anthropic/claude-sonnet-5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4-1" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-opus-5" | "anthropic/claude-opus-5-5";
|
|
99
|
+
type QgridSupportedModel = "openai/gpt-6-astra" | "openai/gpt-6.1-sol" | "openai/gpt-6-sol" | "openai/gpt-6-luna" | "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/gpt-5.6-luna" | "openai/gpt-5.5" | "openai/gpt-5.4" | "openai/gpt-5.2" | "openai/gpt-5.4-mini" | "openai/gpt-5.3-codex" | "openai/gpt-5.3-codex-spark" | "anthropic/claude-fable-5-1" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-4-7" | "anthropic/claude-sonnet-5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4-1" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-opus-5" | "anthropic/claude-opus-5-5" | "anthropic/claude-sonnet-5-5";
|
|
100
100
|
/** Observed image response values. Usage is response-level and appears on the first image only. */
|
|
101
101
|
type QgridImageGenerationMetadata = {
|
|
102
102
|
route: "codex-images";
|