mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-16 10:15:00 +00:00
Merge remote-tracking branch 'origin/main' into branding-upd
# Conflicts: # docsgpt/core/models/anthropic.yaml # docsgpt/core/models/openai.yaml # frontend/src/admin/AdminUI.tsx
This commit is contained in:
Alex committed
commit
a25bec6821
300 files changed
+27029
-1745
No files matched your search
@@ -108,8 +108,10 @@ defaults: # optional, applied to every model below
|
||||
supports_streaming: bool # default true
|
||||
attachments: [<alias-or-mime>, ...] # default []
|
||||
context_window: int # default 128000
|
||||
input_cost_per_token: float # default null
|
||||
output_cost_per_token: float # default null
|
||||
input_cost_per_million: float # USD per 1M prompt tokens; default null (unpriced)
|
||||
output_cost_per_million: float # USD per 1M generated tokens; default null
|
||||
cached_input_cost_per_million: float # prompt-cache reads; default: the input rate
|
||||
cache_write_cost_per_million: float # prompt-cache writes; default: the input rate
|
||||
reasoning_effort: <string> # default null; none|minimal|low|medium|high|xhigh (subset is model-dependent)
|
||||
api_flavor: <string> # chat_completions (default) or responses
|
||||
|
||||
|
||||
@@ -10,17 +10,29 @@ models:
|
||||
description: Most capable Claude model for complex reasoning and agentic coding
|
||||
context_window: 1000000
|
||||
supports_structured_output: true
|
||||
input_cost_per_million: 5.0
|
||||
output_cost_per_million: 25.0
|
||||
cached_input_cost_per_million: 0.5
|
||||
cache_write_cost_per_million: 6.25
|
||||
|
||||
- id: claude-sonnet-4-6
|
||||
display_name: Claude Sonnet 4.6
|
||||
description: Best balance of speed and intelligence with extended thinking
|
||||
context_window: 1000000
|
||||
supports_structured_output: true
|
||||
input_cost_per_million: 3.0
|
||||
output_cost_per_million: 15.0
|
||||
cached_input_cost_per_million: 0.3
|
||||
cache_write_cost_per_million: 3.75
|
||||
|
||||
- id: claude-haiku-4-5
|
||||
display_name: Claude Haiku 4.5
|
||||
description: Fastest Claude model with near-frontier intelligence
|
||||
supports_structured_output: true
|
||||
input_cost_per_million: 1.0
|
||||
output_cost_per_million: 5.0
|
||||
cached_input_cost_per_million: 0.1
|
||||
cache_write_cost_per_million: 1.25
|
||||
|
||||
- id: claude-fable-5
|
||||
display_name: Claude Fable 5
|
||||
|
||||
@@ -12,7 +12,11 @@ models:
|
||||
- id: deepseek-v4-flash
|
||||
display_name: DeepSeek V4 Flash
|
||||
description: Cost-efficient 1M-context model with hybrid thinking / non-thinking modes, tool calling and FIM completion
|
||||
input_cost_per_million: 0.14
|
||||
output_cost_per_million: 0.28
|
||||
|
||||
- id: deepseek-v4-pro
|
||||
display_name: DeepSeek V4 Pro
|
||||
description: Frontier 1M-context model with hybrid thinking / non-thinking modes for advanced reasoning and agentic coding
|
||||
input_cost_per_million: 0.435
|
||||
output_cost_per_million: 0.87
|
||||
@@ -7,3 +7,6 @@ models:
|
||||
supports_tools: true
|
||||
attachments: [image]
|
||||
context_window: 1048576
|
||||
input_cost_per_million: 0.15
|
||||
output_cost_per_million: 0.5
|
||||
cached_input_cost_per_million: 0.03
|
||||
@@ -9,9 +9,16 @@ models:
|
||||
- id: gemini-3.1-pro-preview
|
||||
display_name: Gemini 3.1 Pro (preview)
|
||||
description: Most capable Gemini 3 model with advanced reasoning and agentic coding (preview)
|
||||
# Priced at the >200k-token tier; long prompts are common with attachments.
|
||||
input_cost_per_million: 4.0
|
||||
output_cost_per_million: 18.0
|
||||
- id: gemini-3.5-flash
|
||||
display_name: Gemini 3.5 Flash
|
||||
description: Frontier-class Flash for sustained performance on agentic and coding tasks
|
||||
input_cost_per_million: 1.5
|
||||
output_cost_per_million: 9
|
||||
- id: gemini-3.1-flash-lite
|
||||
display_name: Gemini 3.1 Flash-Lite
|
||||
description: Cost-efficient frontier-class multimodal model for high-throughput workloads
|
||||
input_cost_per_million: 0.25
|
||||
output_cost_per_million: 1.5
|
||||
@@ -8,9 +8,16 @@ models:
|
||||
display_name: GPT-OSS 120B
|
||||
description: OpenAI's open-weight 120B flagship served on Groq's LPU hardware; strong general reasoning with strict structured output support
|
||||
supports_structured_output: true
|
||||
input_cost_per_million: 0.15
|
||||
output_cost_per_million: 0.6
|
||||
cached_input_cost_per_million: 0.075
|
||||
- id: llama-3.3-70b-versatile
|
||||
display_name: Llama 3.3 70B Versatile
|
||||
description: Meta's Llama 3.3 70B for general-purpose chat with parallel tool use
|
||||
input_cost_per_million: 0.59
|
||||
output_cost_per_million: 0.79
|
||||
- id: llama-3.1-8b-instant
|
||||
display_name: Llama 3.1 8B Instant
|
||||
description: Small, very low-latency Llama model (~560 tok/s) with parallel tool use
|
||||
input_cost_per_million: 0.05
|
||||
output_cost_per_million: 0.08
|
||||
@@ -8,14 +8,20 @@ models:
|
||||
display_name: DeepSeek V4 Pro
|
||||
description: 1.6T MoE (49B active) with 1M context, hybrid CSA/HCA attention, top-tier reasoning and agentic coding
|
||||
context_window: 1048576
|
||||
input_cost_per_million: 1.6
|
||||
output_cost_per_million: 3.2
|
||||
|
||||
- id: moonshotai/kimi-k2.6
|
||||
display_name: Kimi K2.6
|
||||
description: 1T-parameter open-weight MoE with native vision/video, multi-step tool calling, and agentic long-horizon execution
|
||||
attachments: [image]
|
||||
context_window: 262144
|
||||
input_cost_per_million: 0.8
|
||||
output_cost_per_million: 3.4
|
||||
|
||||
- id: zai-org/glm-5
|
||||
display_name: GLM-5
|
||||
description: Z.AI 754B-parameter MoE with strong general reasoning, function calling, and structured output
|
||||
context_window: 202800
|
||||
input_cost_per_million: 1.0
|
||||
output_cost_per_million: 3.2
|
||||
@@ -12,12 +12,22 @@ models:
|
||||
context_window: 1050000
|
||||
api_flavor: responses
|
||||
reasoning_effort: medium
|
||||
# Short-context rates. Prompts over 272K tokens bill at $10 / $45 (cached $1).
|
||||
input_cost_per_million: 5.0
|
||||
output_cost_per_million: 30.0
|
||||
cached_input_cost_per_million: 0.5
|
||||
- id: gpt-5.4-mini
|
||||
display_name: GPT-5.4 Mini
|
||||
description: Cost-efficient GPT-5.4-class model for high-volume coding, computer use, and subagent workloads
|
||||
input_cost_per_million: 0.75
|
||||
output_cost_per_million: 4.5
|
||||
cached_input_cost_per_million: 0.075
|
||||
- id: gpt-5.4-nano
|
||||
display_name: GPT-5.4 Nano
|
||||
description: Cheapest GPT-5.4-class model, optimized for simple high-volume tasks where speed and cost matter most
|
||||
input_cost_per_million: 0.2
|
||||
output_cost_per_million: 1.25
|
||||
cached_input_cost_per_million: 0.02
|
||||
- id: gpt-5.6-sol
|
||||
display_name: GPT-5.6 Sol
|
||||
description: Latest GPT-5.6 generation flagship for long-horizon reasoning and agentic work
|
||||
|
||||
@@ -10,16 +10,25 @@ models:
|
||||
description: Free-tier 480B MoE coder model with strong agentic tool use; rate-limited
|
||||
context_window: 262000
|
||||
attachments: []
|
||||
input_cost_per_million: 0.0
|
||||
output_cost_per_million: 0.0
|
||||
|
||||
- id: deepseek/deepseek-v3.2
|
||||
display_name: DeepSeek V3.2
|
||||
description: Open-weights reasoning model, very low cost (~$0.25 in / $0.38 out per 1M)
|
||||
description: Open-weights reasoning model, very low cost (~$0.27 in / $0.40 out per 1M)
|
||||
context_window: 131072
|
||||
attachments: []
|
||||
supports_structured_output: true
|
||||
input_cost_per_million: 0.269
|
||||
output_cost_per_million: 0.4
|
||||
cached_input_cost_per_million: 0.1345
|
||||
|
||||
- id: anthropic/claude-sonnet-4.6
|
||||
display_name: Claude Sonnet 4.6 (via OpenRouter)
|
||||
description: Frontier Sonnet-class model with 1M context, vision, and extended thinking
|
||||
context_window: 1000000
|
||||
supports_structured_output: true
|
||||
input_cost_per_million: 3.0
|
||||
output_cost_per_million: 15.0
|
||||
cached_input_cost_per_million: 0.3
|
||||
cache_write_cost_per_million: 3.75
|
||||
Reference in new issue
Block a user