Skip to content

feat: add recent AI models (GPT Image 2, Claude Opus 4.7, Qwen3.6, DeepSeek V4 Pro[1M], Kimi K2.6, Grok 4.20, MiMo V2.5) #592

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

Closed
wahajahmed010 wants to merge 1 commit into from
+21 −4
Closed

feat: add recent AI models (GPT Image 2, Claude Opus 4.7, Qwen3.6, DeepSeek V4 Pro[1M], Kimi K2.6, Grok 4.20, MiMo V2.5) #592

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
7 changes: 4 additions & 3 deletions .env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ GOOGLE_MODELS=

DEEPSEEK_API_KEY=
DEEPSEEK_BASE_URL=
# Example: deepseek-v4-pro,deepseek-v4-flash
# Example: deepseek-v4-pro,deepseek-v4-pro[1m],deepseek-v4-flash
DEEPSEEK_MODELS=

QWEN_API_KEY=
Expand Down Expand Up @@ -53,18 +53,19 @@ DOUBAO_MODELS=

OPENROUTER_API_KEY=
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
# Example: deepseek/deepseek-v4-pro,deepseek/deepseek-v4-flash
# Example: deepseek/deepseek-v4-pro,deepseek/deepseek-v4-flash,grok-4.20-reasoning,grok-4.20,grok-4.20-multi-agent
OPENROUTER_MODELS=

GROK_API_KEY=
GROK_BASE_URL=
# Example: grok-4.20-reasoning,grok-4.20,grok-4.20-multi-agent
GROK_MODELS=

TENCENT_API_KEY=
# Tencent TokenHub OpenAI-compatible endpoint. Hy3 is a model ID, not an env prefix.
# TENCENT_HUNYUAN_* is also accepted as an alias.
TENCENT_BASE_URL=https://tokenhub.tencentmaas.com/v1
# Example: hy3-preview,hunyuan-2.0-thinking-20251109,hunyuan-2.0-instruct-20251111
# Example: hy3-preview,hunyuan-2.0-thinking-20251109,hunyuan-2.0-instruct-20251111 (note: HY3 is a model name, not an env prefix)
TENCENT_MODELS=

XIAOMI_API_KEY=
Expand Down
16 changes: 16 additions & 0 deletions lib/ai/providers.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -586,6 +586,22 @@ export const PROVIDERS: Record<ProviderId, ProviderConfig> = {
},
},
},
{
id: 'deepseek-v4-pro[1m]',
name: 'DeepSeek V4 Pro (1M)',
contextWindow: 1048576,
outputWindow: 393216,
capabilities: {
streaming: true,
tools: true,
vision: false,
thinking: {
toggleable: true,
budgetAdjustable: true,
defaultEnabled: true,
},
},
},
{
id: 'deepseek-v4-flash',
name: 'DeepSeek V4 Flash',
Expand Down
2 changes: 1 addition & 1 deletion tests/ai/thinking-config.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ describe('thinking config metadata', () => {
expect(glmModels).not.toContain('glm-4.5-flash');
expect(googleModels).toContain('gemini-3.1-pro-preview');
expect(googleModels).not.toContain('gemini-3-pro-preview');
expect(deepseekModels).toEqual(['deepseek-v4-pro', 'deepseek-v4-flash']);
expect(deepseekModels).toEqual(['deepseek-v4-pro', 'deepseek-v4-pro[1m]', 'deepseek-v4-flash']);
expect(hunyuanModels).toEqual(['hy3-preview']);
expect(minimaxModels).toEqual(['MiniMax-M2.7']);
expect(siliconflowModels).not.toContain('MiniMaxAI/MiniMax-M2');
Expand Down
Loading