Skip to content

chore(cognitive): update AI model catalog #6

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 1 commit into
base: master
Choose a base branch
from
Open

chore(cognitive): update AI model catalog #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
156 changes: 154 additions & 2 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 +4,128 @@ 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 Anthropic's most capable model, featuring adaptive reasoning and exceptional performance across complex tasks. It delivers state-of-the-art results on coding, analysis, and agentic workflows, with a 1M token context window.",
lifecycle: 'production',
health: 'healthy',
releaseDate: '2026-01-20',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 1_000_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 is Anthropic's latest flagship Sonnet model, offering top-tier performance for agentic and coding workflows with a 1M token context window. It delivers state-of-the-art results on coding benchmarks and reasoning tasks.",
lifecycle: 'production',
health: 'healthy',
releaseDate: '2026-01-20',
capabilities: {
supportsText: true,
supportsImages: true,
supportsTools: true,
supportsJsonMode: false,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 1_000_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 Anthropic's high-performance Opus model, excelling in complex reasoning, coding, and long-context tasks.",
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 powerful Opus-tier model optimized for complex tasks requiring extended reasoning and high accuracy.",
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-sonnet-4-5-20250929',
displayName: 'Claude Sonnet 4.5',
Expand Down Expand Up @@ -36,6 +156,36 @@ export const ANTHROPIC_CONFIG: ProviderConfig = {
},
tags: ['recommended', '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 frontier Opus model from May 2025, designed for complex reasoning, advanced coding, and long-horizon 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-4-20250514',
displayName: 'Claude Sonnet 4',
Expand Down Expand Up @@ -320,9 +470,11 @@ 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',
replacementModels: ['claude-haiku-4-5-20251001'],
capabilities: {
supportsText: true,
supportsImages: true,
Expand Down
56 changes: 56 additions & 0 deletions packages/cognitive/src/features/providers/cerebras/cerebras.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 CEREBRAS_CONFIG: ProviderConfig = {
description: 'Cerebras AI models for high-performance language processing',
defaultModel: 'gpt-oss-120b',
models: [
{
id: 'qwen-3-235b-a22b-instruct-2507',
displayName: 'Qwen3 235B A22B Instruct',
description:
'Qwen3 235B A22B Instruct is a large mixture-of-experts reasoning model from Alibaba with 235B parameters and 22B active per forward pass. It delivers strong performance on reasoning, code generation, and agentic tasks.',
capabilities: {
supportsText: true,
supportsImages: false,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 131_000,
maxOutputTokens: 16_000,
},
cost: {
inputCostPer1mTokens: 0.8,
outputCostPer1mTokens: 1.6,
},
tags: ['preview', 'general-purpose', 'reasoning'],
releaseDate: '2025-07-01',
lifecycle: 'preview',
},
{
id: 'zai-glm-4.7',
displayName: 'Z.ai GLM 4.7',
description:
'Z.ai GLM 4.7 is a large-scale language model from Zhipu AI with 355B parameters, delivering strong performance across reasoning, coding, and multilingual tasks.',
capabilities: {
supportsText: true,
supportsImages: false,
supportsTools: true,
supportsJsonMode: true,
supportsSystemMessages: true,
supportsStreaming: true,
supportsReasoning: true,
supportsStopSequence: true,
supportsTemperature: true,
},
limits: {
maxInputTokens: 131_000,
maxOutputTokens: 16_000,
},
cost: {
inputCostPer1mTokens: 0.39,
outputCostPer1mTokens: 1.75,
},
tags: ['preview', 'general-purpose', 'reasoning'],
releaseDate: '2025-08-01',
lifecycle: 'preview',
},
{
id: 'gpt-oss-120b',
displayName: 'GPT-OSS 120B (Preview)',
Expand Down
90 changes: 87 additions & 3 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 +6,90 @@ 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: 'deepseek-v3p2',
internalModelId: 'accounts/fireworks/models/deepseek-v3p2',
displayName: 'DeepSeek V3.2',
description:
'DeepSeek V3.2 is the latest iteration of the DeepSeek V3 series, a 685B-parameter mixture-of-experts model with improved reasoning, instruction following, and coding performance.',
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: 'deepseek-v3p1',
internalModelId: 'accounts/fireworks/models/deepseek-v3p1',
displayName: 'DeepSeek V3.1',
description:
'DeepSeek V3.1 is an updated version of the DeepSeek V3 series with enhanced reasoning and instruction-following capabilities.',
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: ['general-purpose', 'coding'],
lifecycle: 'production',
},
{
id: 'kimi-k2-instruct-0905',
internalModelId: 'accounts/fireworks/models/kimi-k2-instruct-0905',
displayName: 'Kimi K2 Instruct 0905',
description:
'Kimi K2 Instruct 0905 from Moonshot AI is an updated version optimized for agentic tasks, complex reasoning, and coding with a large 262k context window.',
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: 'gpt-oss-20b',
internalModelId: 'accounts/fireworks/models/gpt-oss-20b',
Expand Down Expand Up @@ -109,12 +193,12 @@ export const FIREWORKS_CONFIG: ProviderConfig = {
supportsTemperature: true,
},
limits: {
maxInputTokens: 160_000,
maxInputTokens: 163_840,
maxOutputTokens: 16_384,
},
cost: {
inputCostPer1mTokens: 0.9,
outputCostPer1mTokens: 0.9,
inputCostPer1mTokens: 0.56,
outputCostPer1mTokens: 1.68,
},
tags: ['recommended', 'general-purpose'],
lifecycle: 'production',
Expand Down
Loading