Skip to content

chore(cognitive): update AI model catalog #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
github-actions wants to merge 2 commits into
base: master
Choose a base branch
from
Open

chore(cognitive): update AI model catalog #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4726804
chore(cognitive): update AI model catalog
allardy Mar 7, 2026
bc7cf54
chore(cognitive): apply model adjustment
github-actions[bot] Mar 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
157 changes: 154 additions & 3 deletions packages/cognitive/src/features/providers/anthropic/anthropic.config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,156 @@ export const ANTHROPIC_CONFIG: ProviderConfig = {
id: 'anthropic',
name: 'Anthropic',
description: 'Claude models focused on safety and helpfulness',
defaultModel: 'claude-sonnet-4-5-20250929',
defaultModel: 'claude-sonnet-4-6',
models: [
{
id: 'claude-opus-4-6',
displayName: 'Claude Opus 4.6',
aliases: ['claude-opus-4-6'],
description:
'Claude Opus 4.6 is the most intelligent Claude model for building agents and coding. It offers state-of-the-art performance on complex reasoning, coding, and agentic tasks with a 200K context window.',
lifecycle: 'production',
health: 'healthy',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 200_000,
maxOutputTokens: 128_000,
},
cost: {
inputCostPer1mTokens: 5,
outputCostPer1mTokens: 25,
},
tags: ['recommended', 'reasoning', 'agents', 'vision', 'general-purpose', 'coding'],
},
{
id: 'claude-sonnet-4-6',
displayName: 'Claude Sonnet 4.6',
aliases: ['claude-sonnet-4-6'],
description:
'Claude Sonnet 4.6 offers the best combination of speed and intelligence. It delivers strong performance across coding, reasoning, and agentic workflows with a 200K context window.',
lifecycle: 'production',
health: 'healthy',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 200_000,
maxOutputTokens: 64_000,
},
cost: {
inputCostPer1mTokens: 3,
outputCostPer1mTokens: 15,
},
tags: ['recommended', 'reasoning', 'agents', 'vision', 'general-purpose', 'coding'],
},
{
id: 'claude-opus-4-5-20251101',
displayName: 'Claude Opus 4.5',
aliases: ['claude-opus-4-5'],
description:
'Claude Opus 4.5 is a powerful model for complex tasks requiring deep reasoning and coding capabilities, offering near-frontier intelligence with a 200K context window.',
lifecycle: 'production',
health: 'healthy',
releaseDate: '2025-11-01',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 200_000,
maxOutputTokens: 64_000,
},
cost: {
inputCostPer1mTokens: 5,
outputCostPer1mTokens: 25,
},
tags: ['reasoning', 'agents', 'vision', 'general-purpose', 'coding'],
},
{
id: 'claude-opus-4-1-20250805',
displayName: 'Claude Opus 4.1',
aliases: ['claude-opus-4-1'],
description:
'Claude Opus 4.1 is a high-capability model optimized for complex reasoning and agentic tasks with a 200K context window.',
lifecycle: 'production',
health: 'healthy',
releaseDate: '2025-08-05',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 200_000,
maxOutputTokens: 32_000,
},
cost: {
inputCostPer1mTokens: 15,
outputCostPer1mTokens: 75,
},
tags: ['reasoning', 'agents', 'vision', 'general-purpose', 'coding'],
},
{
id: 'claude-opus-4-20250514',
displayName: 'Claude Opus 4',
aliases: ['claude-opus-4-0'],
description:
'Claude Opus 4 is Anthropic\'s first model in the Claude 4 family, delivering frontier-level intelligence for complex reasoning, coding, and agentic tasks.',
lifecycle: 'production',
health: 'healthy',
releaseDate: '2025-05-14',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 200_000,
maxOutputTokens: 32_000,
},
cost: {
inputCostPer1mTokens: 15,
outputCostPer1mTokens: 75,
},
tags: ['reasoning', 'agents', 'vision', 'general-purpose', 'coding'],
},
{
id: 'claude-sonnet-4-5-20250929',
displayName: 'Claude Sonnet 4.5',
Expand Down Expand Up @@ -320,9 +468,12 @@ export const ANTHROPIC_CONFIG: ProviderConfig = {
displayName: 'Claude 3 Haiku',
description:
"Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance.",
lifecycle: 'production',
lifecycle: 'deprecated',
health: 'healthy',
releaseDate: '2024-03-07',
deprecationDate: '2026-04-19',
discontinuedDate: '2026-04-19',
replacementModels: ['claude-haiku-4-5-20251001'],
capabilities: {
supportsText: true,
supportsImages: true,
Expand All @@ -342,7 +493,7 @@ export const ANTHROPIC_CONFIG: ProviderConfig = {
inputCostPer1mTokens: 0.25,
outputCostPer1mTokens: 1.25,
},
tags: ['low-cost', 'general-purpose'],
tags: ['deprecated', 'low-cost', 'general-purpose'],
},
],
}
56 changes: 56 additions & 0 deletions packages/cognitive/src/features/providers/fireworks-ai/fireworks.config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,62 @@ export const FIREWORKS_CONFIG: ProviderConfig = {
description: 'Fireworks AI provides fast inference for various language models',
defaultModel: 'accounts/fireworks/models/llama-v3p1-70b-instruct',
models: [
{
id: 'kimi-k2-instruct',
internalModelId: 'accounts/fireworks/models/kimi-k2-instruct',
displayName: 'Kimi K2 Instruct',
description:
'Kimi K2 is a state-of-the-art language model from Moonshot AI with strong agentic capabilities, tool use, and long-context reasoning. Optimized for complex instruction-following, coding, and multi-step tasks.',
capabilities: {
supportsText: true,
supportsImages: false,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 262_144,
maxOutputTokens: 16_384,
},
cost: {
inputCostPer1mTokens: 0.6,
outputCostPer1mTokens: 2.5,
},
tags: ['general-purpose', 'reasoning', 'coding'],
lifecycle: 'production',
},
{
id: 'deepseek-v3p1',
internalModelId: 'accounts/fireworks/models/deepseek-v3p1',
displayName: 'DeepSeek V3.1',
description:
'DeepSeek V3.1 is the latest iteration of the DeepSeek V3 family, a 685B-parameter mixture-of-experts model. It delivers improved performance across reasoning, coding, and general-purpose tasks at a lower cost than its predecessors.',
capabilities: {
supportsText: true,
supportsImages: false,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: false,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 163_840,
maxOutputTokens: 16_384,
},
cost: {
inputCostPer1mTokens: 0.56,
outputCostPer1mTokens: 1.68,
},
tags: ['recommended', 'general-purpose', 'coding'],
lifecycle: 'production',
},
{
id: 'gpt-oss-20b',
internalModelId: 'accounts/fireworks/models/gpt-oss-20b',
Expand Down
84 changes: 84 additions & 0 deletions packages/cognitive/src/features/providers/google-ai/google-ai.config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,62 @@ export const GOOGLE_AI_CONFIG: ProviderConfig = {
description: 'Gemini models from Google with multimodal capabilities',
defaultModel: 'gemini-2.5-flash',
models: [
{
id: 'gemini-3.1-pro',
internalModelId: 'gemini-3.1-pro-preview',
displayName: 'Gemini 3.1 Pro',
description:
"Google's most advanced model with state-of-the-art reasoning, agentic capabilities, and multimodal understanding. Delivers richer visuals and deeper interactivity built on frontier-level reasoning.",
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 1_048_576,
maxOutputTokens: 65_536,
},
cost: {
inputCostPer1mTokens: 2,
outputCostPer1mTokens: 12,
},
tags: ['reasoning', 'agents', 'general-purpose', 'vision'],
lifecycle: 'preview',
},
{
id: 'gemini-3.1-flash-lite',
internalModelId: 'gemini-3.1-flash-lite-preview',
displayName: 'Gemini 3.1 Flash-Lite',
description:
"Google's most cost-effective frontier-class model, designed for speed and high-volume tasks with strong intelligence at a fraction of the cost.",
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 1_048_576,
maxOutputTokens: 65_536,
},
cost: {
inputCostPer1mTokens: 0.25,
outputCostPer1mTokens: 1.5,
},
tags: ['low-cost', 'general-purpose', 'vision'],
lifecycle: 'preview',
},
{
id: 'gemini-3-pro',
internalModelId: 'gemini-3-pro-preview',
Expand Down Expand Up @@ -63,6 +119,34 @@ export const GOOGLE_AI_CONFIG: ProviderConfig = {
releaseDate: '2025-12-17',
lifecycle: 'preview',
},
{
id: 'gemini-2.5-flash-lite',
displayName: 'Gemini 2.5 Flash-Lite',
description:
"Google's fastest and most budget-friendly Gemini 2.5 model, optimized for high-volume, low-latency tasks while maintaining strong multimodal capabilities.",
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 1_048_576,
maxOutputTokens: 65_536,
},
cost: {
inputCostPer1mTokens: 0.1,
outputCostPer1mTokens: 0.4,
},
tags: ['low-cost', 'general-purpose', 'vision'],
releaseDate: '2025-06-01',
lifecycle: 'production',
},
{
id: 'gemini-2.5-flash',
displayName: 'Gemini 2.5 Flash',
Expand Down
Loading