lee/puter
1
0
Fork 0
mirror of https://github.com/HeyPuter/puter.git synced 2026-09-12 00:05:38 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

feat(ai): backfill provider catalogs from live /models listings

Browse Source 
A live audit of every keyed provider's /models endpoint against the hardcoded
catalogs found no stale entries but large gaps. This backfills them under four
rules: nothing vendor-deprecated, nothing without a price confirmed on the
vendor's official pricing page (each entry's source was recorded during
review), nothing absent from the live /models listing, and nothing that fails
a live routing probe.

Added: 46 Alibaba entries (qwen3/3.5/3.7/3.8 families, VL/omni/MT lines, and
Model Studio's hosted GLM/DeepSeek/Kimi third-party models) plus 9 dated
aliases; OpenAI chat-latest and gpt-4o-2024-11-20 plus 16 snapshot aliases;
Gemini gemma-4-31b-it and gemma-4-26b-a4b-it (vendor-documented free tier)
plus rolling -latest aliases; Mistral-hosted zai-glm-5-2 and a
mistral-medium-3.5 alias; deepseek-v4-flash-vision-exp; glm-5.3-flash.

Culled by the rules: 15 vendor-deprecated OpenAI entries (the 3.5/4/4-turbo
legacy line, gpt-4o-2024-05-13, o1-pro, four chat-latest predecessors, the
5.x codex line — deprecations page, most shut down 2026-10-23) and dated
aliases onto the deprecated o1/o3-mini/o4-mini; qwen3-vl-flash-2025-10-15
(live routing probe returned upstream 400 twice). Tiered Alibaba prices are
encoded at the base tier and busy-hour rates where time-of-day priced, noted
in comments.

Every surviving addition was verified end-to-end through a local deployment:
58/58 answered a live prompt, including all 46 Alibaba entries and every
spot-checked alias.

Not changed, flagged for maintainers: pre-existing o1, o3-mini and o4-mini
entries are now vendor-deprecated (shutdown 2026-10-23); the pre-existing
deepseek-v4-flash/-pro prices no longer match DeepSeek's current pricing
page; gemma-4 emits its own <thought> markup inline in content.

Co-Authored-By: Claude Fable 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
404oops
2026-08-30 20:50:46 +02:00
co-authored by Claude Fable 5
parent 4199a2506d
commit 7e1cdefd98
6 changed files with 1218 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/backend/drivers/ai-chat/providers/alibaba/models.ts
+1027 -4
View File
File diff suppressed because it is too large Load Diff
src/backend/drivers/ai-chat/providers/deepseek/models.ts
+25
View File
@@ -50,6 +50,31 @@ export const DEEPSEEK_MODELS: IChatModel[] = [
},
max_tokens: 384_000,
},
{
// Priced identically to deepseek-v4-flash per DeepSeek's launch note
// (https://api-docs.deepseek.com/news/news260821/) and the pricing
// page, which lists the same rates for both models; images are
// tokenized (up to 384 tokens each) and billed as input tokens.
puterId: 'deepseek:deepseek/deepseek-v4-flash-vision-exp',
id: 'deepseek-v4-flash-vision-exp',
modalities: { input: ['text', 'image'], output: ['text'] },
open_weights: false,
tool_call: true,
release_date: '2026-08-21',
name: 'DeepSeek V4 Flash Vision (Experimental)',
aliases: ['deepseek/deepseek-v4-flash-vision-exp'],
context: 1_000_000,
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
costs: {
tokens: 1_000_000,
prompt_tokens: 14,
completion_tokens: 28,
cached_tokens: 0.28,
},
max_tokens: 384_000,
},
{
puterId: 'deepseek:deepseek/deepseek-v4-pro',
id: 'deepseek-v4-pro',
src/backend/drivers/ai-chat/providers/gemini/models.ts
+79 -3
View File
@@ -33,7 +33,14 @@ export const GEMINI_MODELS: IChatModel[] = [
knowledge: '2025-01',
release_date: '2026-05-19',
name: 'Gemini 3.5 Flash',
aliases: ['google/gemini-3.5-flash'],
aliases: [
'google/gemini-3.5-flash',
// Rolling alias; Gemini API changelog (2026-05-19): gemini-3.5-flash
// "Now backs `gemini-flash-latest`". Hot-swapped by Google on new
// releases; no later switch documented as of 2026-08-28.
'gemini-flash-latest',
'google/gemini-flash-latest',
],
context: 1_048_576,
max_tokens: 65_536,
costs_currency: 'usd-cents',
@@ -61,7 +68,13 @@ export const GEMINI_MODELS: IChatModel[] = [
knowledge: '2025-01',
release_date: '2026-07-21',
name: 'Gemini 3.5 Flash-Lite',
aliases: ['google/gemini-3.5-flash-lite'],
aliases: [
'google/gemini-3.5-flash-lite',
// Rolling alias that floats across Flash-Lite releases; pinned here
// to the newest Flash-Lite in this catalog (GA 2026-07-21).
'gemini-flash-lite-latest',
'google/gemini-flash-lite-latest',
],
context: 1_048_576,
max_tokens: 65_536,
costs_currency: 'usd-cents',
@@ -228,7 +241,14 @@ export const GEMINI_MODELS: IChatModel[] = [
knowledge: '2025-01',
release_date: '2026-02-19',
name: 'Gemini 3.1 Pro Preview',
aliases: ['google/gemini-3.1-pro-preview'],
aliases: [
'google/gemini-3.1-pro-preview',
// Rolling alias that floats across Pro releases; pinned here to the
// newest Pro in this catalog (Google last documented it switching to
// gemini-3-pro-preview on 2026-01-21, superseded by 3.1 on 2026-02-19).
'gemini-pro-latest',
'google/gemini-pro-latest',
],
context: 1_048_576,
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
@@ -301,4 +321,60 @@ export const GEMINI_MODELS: IChatModel[] = [
},
max_tokens: 65536,
},
{
puterId: 'google:google/gemma-4-31b-it',
id: 'gemma-4-31b-it',
modalities: {
input: ['text', 'image'],
output: ['text'],
},
open_weights: true,
tool_call: true,
knowledge: '2025-01',
release_date: '2026-04-02',
name: 'Gemma 4 31B',
aliases: ['google/gemma-4-31b-it'],
context: 262_144,
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
// Gemma 4 on the Gemini API is free of charge (free tier only; the
// official pricing page lists no paid tier for Gemma models).
costs: {
tokens: 1_000_000,
prompt_tokens: 0,
completion_tokens: 0,
thinking_tokens: 0,
cached_tokens: 0,
},
max_tokens: 8_192,
},
{
puterId: 'google:google/gemma-4-26b-a4b-it',
id: 'gemma-4-26b-a4b-it',
modalities: {
input: ['text', 'image'],
output: ['text'],
},
open_weights: true,
tool_call: true,
knowledge: '2025-01',
release_date: '2026-04-02',
name: 'Gemma 4 26B A4B',
aliases: ['google/gemma-4-26b-a4b-it'],
context: 262_144,
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
// Gemma 4 on the Gemini API is free of charge (free tier only; the
// official pricing page lists no paid tier for Gemma models).
costs: {
tokens: 1_000_000,
prompt_tokens: 0,
completion_tokens: 0,
thinking_tokens: 0,
cached_tokens: 0,
},
max_tokens: 8_192,
},
];
src/backend/drivers/ai-chat/providers/mistral/models.ts
+24
View File
@@ -32,6 +32,7 @@ export const MISTRAL_MODELS: IChatModel[] = [
name: 'Mistral Medium 3.5',
aliases: [
'mistral-medium-3-5',
'mistral-medium-3.5',
'mistral-medium-3',
'mistral-medium-latest',
'mistral-medium',
@@ -110,6 +111,29 @@ export const MISTRAL_MODELS: IChatModel[] = [
completion_tokens: 60,
},
},
{
puterId: 'mistralai:mistralai/zai-glm-5-2',
id: 'zai-glm-5-2',
modalities: { input: ['text'], output: ['text'] },
open_weights: true,
tool_call: true,
release_date: '2026-08-06',
name: 'Z.ai GLM 5.2',
aliases: ['glm-5-2'],
context: 1_000_000,
max_tokens: 128_000,
description:
'Third-party open-source model from Z.ai, hosted by Mistral for long-context coding and agentic workflows.',
provider: 'mistral',
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
costs: {
tokens: 1_000_000,
prompt_tokens: 140,
completion_tokens: 440,
},
},
{
puterId: 'mistralai:mistralai/codestral-2508',
id: 'codestral-2508',
src/backend/drivers/ai-chat/providers/openai/models.ts
+53 -12
View File
@@ -158,7 +158,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2025-08-31',
release_date: '2026-03-05',
aliases: ['openai/gpt-5.4-pro'],
aliases: ['gpt-5.4-pro-2026-03-05', 'openai/gpt-5.4-pro'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -178,7 +178,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
open_weights: false,
tool_call: true,
knowledge: '2025-08-31',
aliases: ['openai/gpt-5.4-mini'],
aliases: ['gpt-5.4-mini-2026-03-17', 'openai/gpt-5.4-mini'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -200,7 +200,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2025-08-31',
release_date: '2026-03-19',
aliases: ['openai/gpt-5.4-nano'],
aliases: ['gpt-5.4-nano-2026-03-17', 'openai/gpt-5.4-nano'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -221,7 +221,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2025-10',
release_date: '2025-10-06',
aliases: ['openai/gpt-5-pro'],
aliases: ['gpt-5-pro-2025-10-06', 'openai/gpt-5-pro'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -306,7 +306,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2024-09-30',
release_date: '2025-11-13',
aliases: ['openai/gpt-5.1'],
aliases: ['gpt-5.1-2025-11-13', 'openai/gpt-5.1'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -390,7 +390,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2023-09',
release_date: '2024-05-13',
aliases: ['openai/gpt-4o'],
aliases: ['gpt-4o-2024-08-06', 'openai/gpt-4o'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -411,7 +411,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2023-09',
release_date: '2024-07-18',
aliases: ['openai/gpt-4o-mini'],
aliases: ['gpt-4o-mini-2024-07-18', 'openai/gpt-4o-mini'],
context: 128_000,
max_tokens: 16384,
costs_currency: 'usd-cents',
@@ -453,7 +453,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2024-05',
release_date: '2025-04-16',
aliases: ['openai/o3'],
aliases: ['o3-2025-04-16', 'openai/o3'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -474,7 +474,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2024-05',
release_date: '2025-06-10',
aliases: ['openai/o3-pro'],
aliases: ['o3-pro-2025-06-10', 'openai/o3-pro'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -537,7 +537,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2024-04',
release_date: '2025-04-14',
aliases: ['openai/gpt-4.1'],
aliases: ['gpt-4.1-2025-04-14', 'openai/gpt-4.1'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -558,7 +558,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2024-04',
release_date: '2025-04-14',
aliases: ['openai/gpt-4.1-mini'],
aliases: ['gpt-4.1-mini-2025-04-14', 'openai/gpt-4.1-mini'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -579,7 +579,7 @@ export const OPEN_AI_MODELS: IChatModel[] = [
tool_call: true,
knowledge: '2024-04',
release_date: '2025-04-14',
aliases: ['openai/gpt-4.1-nano'],
aliases: ['gpt-4.1-nano-2025-04-14', 'openai/gpt-4.1-nano'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
@@ -592,4 +592,45 @@ export const OPEN_AI_MODELS: IChatModel[] = [
context: 1_047_576,
max_tokens: 32768,
},
{
puterId: 'openai:openai/chat-latest',
id: 'chat-latest',
modalities: { input: ['text', 'image'], output: ['text'] },
open_weights: false,
tool_call: true,
knowledge: '2025-08-31',
aliases: ['openai/chat-latest'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
costs: {
tokens: 1_000_000,
prompt_tokens: 500,
cached_tokens: 50,
completion_tokens: 3000,
},
context: 400_000,
max_tokens: 128_000,
},
{
puterId: 'openai:openai/gpt-4o-2024-11-20',
id: 'gpt-4o-2024-11-20',
modalities: { input: ['text', 'image'], output: ['text'] },
open_weights: false,
tool_call: true,
knowledge: '2023-09',
release_date: '2024-11-20',
aliases: ['openai/gpt-4o-2024-11-20'],
costs_currency: 'usd-cents',
input_cost_key: 'prompt_tokens',
output_cost_key: 'completion_tokens',
costs: {
tokens: 1_000_000,
prompt_tokens: 250,
cached_tokens: 125,
completion_tokens: 1000,
},
context: 128_000,
max_tokens: 16_384,
},
];
src/backend/drivers/ai-chat/providers/zai/models.ts
+10
View File
@@ -53,6 +53,16 @@ export const ZAI_MODELS: IChatModel[] = [
128 * K,
usdPerMToken(1.4, 4.4, 0.26),
),
// List price from https://docs.z.ai/guides/overview/pricing ($0.15 in /
// $0.50 out / $0.03 cached per MTok); the page currently shows a 50%
// promotional discount, which we deliberately do not encode.
textModel(
'glm-5.3-flash',
'GLM-5.3-Flash',
1_000 * K,
128 * K,
usdPerMToken(0.15, 0.5, 0.03),
),
textModel(
'glm-5.2',
'GLM-5.2',