@grida/ai-models 1.20261013.1 → 1.20261013.3

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/PROVENANCE.md CHANGED
@@ -1000,3 +1000,75 @@ Another provider's regular rates are not evidence of Grida's advertised rates.
1000
1000
  Other recorded service rates match the inspected discovery.
1001
1001
  This catalogue describes public service facts without supplier selection or
1002
1002
  private financial policy.
1003
+
1004
+ ## GPT-6 Sol, Luna and GPT-6.1 Sol (2026-10-13)
1005
+
1006
+ OpenAI's [Sol and Luna announcement](https://openai.com/index/introducing-gpt-6-sol-and-luna/)
1007
+ and [DevDay announcement](https://openai.com/index/devday-2026-recap/) establish
1008
+ their September 22 and September 29 releases. The native model pages for
1009
+ [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol),
1010
+ [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) and
1011
+ [6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) establish
1012
+ standard regular prices, cache meters and reasoning/API differences. The new
1013
+ prices are regular rates, not the preceding generation's promotion.
1014
+
1015
+ All three support tools in Responses. Native Chat Completions supports tools
1016
+ only with explicit `none` reasoning for Sol and Luna, and does not support tools
1017
+ for 6.1 Sol. A model-level `tools: true` is therefore not a promise about every
1018
+ API interface. Native endpoint records describe Responses; qualifications retain
1019
+ the Chat Completions restrictions.
1020
+
1021
+ [Vercel discovery](https://ai-gateway.vercel.sh/v1/models) preserves the native
1022
+ long-context boundary of 272001 input tokens, while
1023
+ [OpenRouter discovery](https://openrouter.ai/api/v1/models) reports its override
1024
+ at 272000. Provider bindings preserve that difference. Cache writes and reads
1025
+ are separate meters; 6.1 Sol's cached-input rate is half Sol's.
1026
+
1027
+ OpenAI's [vision guide](https://developers.openai.com/api/docs/guides/images-vision)
1028
+ confirms image formats but does not name these three models in its multiplier
1029
+ and detail-sizing tables. Their image-input capability is recorded, but no
1030
+ image-tokenization formula is copied from Astra or GPT-5.6.
1031
+
1032
+ ## Gemini Nano Banana 2.1 (2026-10-13)
1033
+
1034
+ The [native model specification](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/nano-banana-2-1)
1035
+ records October 6 availability, 14 reference images, 1K/2K/4K outputs and the
1036
+ image-token table. Unlike Nano Banana 2, 512px output is not offered.
1037
+ [Google pricing](https://ai.google.dev/gemini-api/docs/pricing) separates input,
1038
+ text/thinking output, image output and search grounding.
1039
+
1040
+ [fal's editing page](https://fal.ai/models/google/nano-banana-2.1/edit) publishes
1041
+ token rates for both generation and editing. Its small-prompt image examples are
1042
+ not flat charges: prompt and input tokens repeat for each generated image,
1043
+ thinking adds text-output tokens, and search results add input tokens. The
1044
+ [generation schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=google/nano-banana-2.1)
1045
+ and [editing schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=google/nano-banana-2.1/edit)
1046
+ retain exact controls. fal lists `seed`, while native Google Cloud declares it
1047
+ unsupported; no deterministic behavior or parameter portability is inferred.
1048
+
1049
+ [Vercel discovery](https://ai-gateway.vercel.sh/v1/models) lists resolution-based
1050
+ output-image price examples and text-token rates. No image-token rate is inferred
1051
+ from Google's price. [OpenRouter discovery](https://openrouter.ai/api/v1/models)
1052
+ publishes separate image-output token pricing and different context/output
1053
+ limits, which remain provider-specific. None of the four new cards claims Grida
1054
+ availability before the public service offers them. No paid inference was used
1055
+ to establish these facts.
1056
+
1057
+ ## Grida provider discovery — 2026-10-14
1058
+
1059
+ Authenticated [Grida model discovery](https://gateway.grida.ai/v1/models),
1060
+ [operation schemas](https://gateway.grida.ai/schemas/operations.json) and the
1061
+ [public API reference](https://gateway.grida.ai/llms.txt) were checked together.
1062
+ They confirm Grida bindings for GPT-6 Sol, GPT-6 Luna, GPT-6.1 Sol and Gemini Nano
1063
+ Banana 2.1. The three text bindings are text-only on Grida; native image-input
1064
+ capabilities remain recorded separately. Nano Banana 2.1 exposes generation and
1065
+ reference editing through distinct schema-linked operations.
1066
+
1067
+ Grida discovery also publishes separate cache-write price components for
1068
+ GPT-5.6 Sol/Terra/Luna and GPT-6 Astra, and regular token schedules for Gemini
1069
+ 3.7 Flash and 3.8 Flash. These replace the earlier Grida price qualifications.
1070
+ All prices here are the advertised USD schedule, with exact billing meters and
1071
+ input-length bands; no inference cost is reconstructed from an example output.
1072
+ This verifies public discovery and contract metadata, not exhaustive inference
1073
+ behavior. Other providers' records, model release dates and intrinsic facts are
1074
+ unchanged.
package/README.md CHANGED
@@ -5,7 +5,7 @@ provider bindings, and published prices, with the labs that make them and their
5
5
  logos. Every fact cites a first-party source.
6
6
 
7
7
  This package is the data, published unchanged from release
8
- [`v1.20261013.1`](https://github.com/gridaco/models/releases/tag/v1.20261013.1) of [gridaco/models](https://github.com/gridaco/models). It contains no code.
8
+ [`v1.20261013.3`](https://github.com/gridaco/models/releases/tag/v1.20261013.3) of [gridaco/models](https://github.com/gridaco/models). It contains no code.
9
9
 
10
10
  | file | contents |
11
11
  | --- | --- |
@@ -25,7 +25,7 @@ From a CDN, without installing:
25
25
 
26
26
  ```
27
27
  https://cdn.jsdelivr.net/npm/@grida/ai-models@1/models.json
28
- https://cdn.jsdelivr.net/npm/@grida/ai-models@1.20261013.1/models.json
28
+ https://cdn.jsdelivr.net/npm/@grida/ai-models@1.20261013.3/models.json
29
29
  ```
30
30
 
31
31
  ## Versions
package/manifest.json CHANGED
@@ -1,19 +1,19 @@
1
1
  {
2
2
  "name": "grida-models",
3
- "version": "v1.20261013.1",
3
+ "version": "v1.20261013.3",
4
4
  "schema_version": 1,
5
- "commit": "e10c3c04c763dae10ab796df317b3105dcd611c4",
6
- "created": "2026-10-13T12:42:45Z",
7
- "source": "https://github.com/gridaco/models/tree/e10c3c04c763dae10ab796df317b3105dcd611c4/catalogue",
8
- "digest": "sha256:ba54f9f0b6ce1c632064796cc443072ac7e7ec89f46f1d282bd734e9add18c50",
5
+ "commit": "174414454b857b2c5aa53d640cd92046e95b19c3",
6
+ "created": "2026-10-13T16:15:42Z",
7
+ "source": "https://github.com/gridaco/models/tree/174414454b857b2c5aa53d640cd92046e95b19c3/catalogue",
8
+ "digest": "sha256:219da3c1eab8971694be825d78f8e931eae76ea8cd97625e86ec57f390b9de7e",
9
9
  "counts": {
10
- "cards": 61,
10
+ "cards": 65,
11
11
  "labs": 14
12
12
  },
13
13
  "files": {
14
14
  "PROVENANCE.md": {
15
- "sha256": "4c0b2ee977523b56abf8f706fafe167d643f9eaeed2021509daf24b789ad77e6",
16
- "bytes": 44757
15
+ "sha256": "a7d0e6e6ce7ba4d72d62e05f2cc67cb2c944099d48244f7acf3ba5a5033c3d6a",
16
+ "bytes": 49205
17
17
  },
18
18
  "README.md": {
19
19
  "sha256": "24dc2be40afb3aa64da8b04e2e664865ac6d3a7b7d5b258adb3c1241cc00d004",
@@ -80,8 +80,8 @@
80
80
  "bytes": 330
81
81
  },
82
82
  "models.json": {
83
- "sha256": "4703e28fd32e45efd792705f204c2f9de12786b5ee9eadf0c6e4d2062b2bec26",
84
- "bytes": 509427
83
+ "sha256": "9f61efaf8e978d3886de1139d2f471db8372e162677715a4352f2793f47af5f5",
84
+ "bytes": 586418
85
85
  },
86
86
  "schemas/labs.schema.json": {
87
87
  "sha256": "9ddaedd56826bebdbe72b84f76cfc86df0b5c5902ba9f0259c2ea2cbb9327f99",