arka/librefang-registry
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: prune deprecated models across providers (#75)

Browse Source 
* chore: prune deprecated models across providers

Remove old-generation models that are strictly superseded by current versions
on the same provider/family. Affected providers: anthropic, bedrock, vertex-ai,
xai, moonshot, zhipu, baichuan, stepfun, volcengine, minimax, cohere, together,
fireworks, deepinfra, openrouter. Also clean up orphan aliases (grok3, grok-mini,
minimax-m2.1) and remap moonshot alias to kimi-k2.5.

Net: -42 model entries across 18 files. Provider model counts and README rows
updated accordingly.

* chore: remove redundant and orphan aliases from aliases.toml

Provider TOML files auto-register their model.aliases at load time, so
re-declaring them globally is duplication. Also drop entries pointing to
models that no longer exist after the prune.

- 45 redundant entries duplicating provider-defined aliases
- 11 orphan targets (gpt-4o, gpt-4o-mini, grok-2-mini, grok-3,
  mixtral-8x7b-32768, copilot/gpt-4, open-mistral-nemo,
  pixtral-large-latest, jamba-1.5-large, palmyra-x5, venice-uncensored)

Net: 100 lines down to 21. The file is now what the header comment
always claimed it was: 'additional global aliases not tied to a specific
model entry.'

* chore: second pass — prune more deprecated models

Apply the same 'strictly superseded by same-provider/family successor'
rule to providers missed in the first pass:

- openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5)
- meta-llama: llama-3.3-70b-instruct (1)
- zhipu: glm-4v-plus (1)
- together: Llama-3.3-70B-Instruct-Turbo (1)
- xiaomi: mimo-v2-flash / -omni / -pro (3)
- aion-labs: aion-1.0 / -mini (2)
- qianfan: ernie-speed-128k, ernie-4.0-turbo-8k (2)
- cerebras: cerebras/llama3.1-8b (1)
- qwen-code: qwen-code/qwq-32b (1)
- nvidia-nim: 12 models (llama-3.1/3.2 series, mixtral-8x22b,
  mistral-small-3.1, phi-4-mini, qwq-32b, r1-distill-32b,
  qwen2.5-coder, nemotron-mini-4b, nemotron-70b-instruct)
- openrouter: meta-llama/llama-3.3-70b (paid), rekaai/reka-edge (2)
- alibaba-coding-plan: qwen3.5-plus, qwen3-max-2026-01-23,
  MiniMax-M2.5, kimi-k2.5 (4)

Net: -35 model entries. providers/README.md model counts updated.
220 models remain.
This commit is contained in:
Evan authored and GitHub committed 2026-04-27 09:36:43 +09:00
1 parent 98ae51444f
commit 541052dc79
27 files changed
+41 -1180
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.github/ISSUE_TEMPLATE/pricing-correction.yml
+1 -1
View File
@@ -16,7 +16,7 @@ body:
attributes:
label: Model ID
description: The canonical model identifier.
placeholder: e.g. gpt-4o, claude-sonnet-4-20250514
placeholder: e.g. gpt-5, claude-sonnet-4-6
validations:
required: true
aliases.toml
+3 -93
View File
@@ -5,106 +5,16 @@
# that are not tied to a specific model entry.
[aliases]
# Anthropic
"sonnet" = "claude-sonnet-4-6"
"claude-sonnet" = "claude-sonnet-4-6"
"haiku" = "claude-haiku-4-5-20251001"
"claude-haiku" = "claude-haiku-4-5-20251001"
"opus" = "claude-opus-4-6"
"claude-opus" = "claude-opus-4-6"
# OpenAI
"gpt4" = "gpt-4o"
"gpt4o" = "gpt-4o"
"gpt4-mini" = "gpt-4o-mini"
"gpt5" = "gpt-5.2"
"gpt5-mini" = "gpt-5-mini"
# Google Gemini
"flash" = "gemini-2.5-flash"
"gemini-pro" = "gemini-3.1-pro-preview"
"gemini-flash" = "gemini-3-flash-preview"
# DeepSeek
"deepseek" = "deepseek-chat"
"deepseek-v3" = "deepseek-chat"
"deepseek-r1" = "deepseek-reasoner"
# Groq
"llama" = "llama-3.3-70b-versatile"
"llama-70b" = "llama-3.3-70b-versatile"
"mixtral" = "mixtral-8x7b-32768"
# Mistral
"mistral" = "mistral-large-latest"
"codestral" = "codestral-latest"
"mistral-nemo" = "open-mistral-nemo"
"pixtral" = "pixtral-large-latest"
# xAI
"grok" = "grok-4-0709"
"grok-4" = "grok-4-0709"
"grok-mini" = "grok-2-mini"
"grok3" = "grok-3"
"grok-fast" = "grok-4-1-fast-reasoning"
# Perplexity
"sonar" = "sonar-pro"
# AI21
"jamba" = "jamba-1.5-large"
# Cohere
"command-r" = "command-r-plus"
"command" = "command-a"
# GitHub Copilot
# GitHub Copilot — bare names not registered on the copilot/gpt-4o model
"copilot" = "copilot/gpt-4o"
"copilot-4o" = "copilot/gpt-4o"
"copilot-4" = "copilot/gpt-4"
"copilot-gpt4o" = "copilot/gpt-4o"
"copilot-gpt4" = "copilot/gpt-4"
# Chinese models
"qwen" = "qwen-plus"
"glm" = "glm-5-20250605"
# Chinese models — common short names not on the canonical model entries
"ernie" = "ernie-4.5-8k"
"kimi" = "kimi-k2"
"moonshot" = "moonshot-v1-128k"
"moonshot" = "kimi-k2.5"
"minimax" = "MiniMax-M2.7"
"minimax-m2.5" = "MiniMax-M2.5"
"minimax-m2.5-highspeed" = "MiniMax-M2.5-highspeed"
"minimax-highspeed" = "MiniMax-M2.7-highspeed"
"minimax-m2.1" = "MiniMax-M2.1"
"codegeex" = "codegeex-4"
"doubao" = "doubao-seed-2-0-pro-260215"
"doubao-seed" = "doubao-seed-2-0-pro-260215"
"stepfun" = "step-3.5-flash"
"baichuan" = "Baichuan4"
"baichuan-4" = "Baichuan4"
# Writer
"palmyra" = "palmyra-x5"
"writer" = "palmyra-x5"
# ChatGPT Session Auth
"chatgpt" = "gpt-5.1-codex-mini"
"chatgpt-mini" = "gpt-5.1-codex-mini"
"chatgpt-5.1" = "gpt-5.1-codex"
"chatgpt-5.2" = "gpt-5.2-codex"
"chatgpt-5.3" = "gpt-5.3-codex"
"chatgpt-5.4" = "gpt-5.4-codex"
# Codex
"codex" = "codex/gpt-4.1"
"codex-4.1" = "codex/gpt-4.1"
"codex-o4" = "codex/o4-mini"
# Venice
"venice" = "venice-uncensored"
# Claude Code
"claude-code" = "claude-code/sonnet"
"claude-code-opus" = "claude-code/opus"
"claude-code-sonnet" = "claude-code/sonnet"
"claude-code-haiku" = "claude-code/haiku"
providers/README.md
+19 -19
View File
@@ -2,7 +2,7 @@
LLM provider and model metadata for LibreFang. Each `.toml` file defines one provider's API configuration and all its available models with pricing, context windows, and capability flags.
**Current state: 46 providers, 232+ models**
**Current state: 46 providers, 220+ models**
---
@@ -13,13 +13,13 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
| ID | Display Name | Base URL | API Key Env | Models | Description |
|----|-------------|----------|-------------|--------|-------------|
| `anthropic` | Anthropic | `https://api.anthropic.com` | `ANTHROPIC_API_KEY` | 7 | Claude family (Haiku / Sonnet / Opus); native Anthropic wire protocol, not OpenAI-compatible |
| `openai` | OpenAI | `https://api.openai.com/v1` | `OPENAI_API_KEY` | 15 | GPT-4.x, o-series reasoning, image generation, TTS; also the fallback for codex-cli |
| `openai` | OpenAI | `https://api.openai.com/v1` | `OPENAI_API_KEY` | 10 | GPT-5.x family + image generation; codex-cli fallback |
| `gemini` | Google Gemini | `https://generativelanguage.googleapis.com` | `GEMINI_API_KEY` | 6 | Gemini 2.x family; native Google GenerativeLanguage protocol |
| `xai` | xAI | `https://api.x.ai/v1` | `XAI_API_KEY` | 7 | Grok-3 family from Elon Musk's xAI |
| `mistral` | Mistral AI | `https://api.mistral.ai/v1` | `MISTRAL_API_KEY` | 3 | Mistral Large / Small / Codestral; European frontier models |
| `cohere` | Cohere | `https://api.cohere.com/v2` | `COHERE_API_KEY` | 4 | Command R+ family; strong RAG and tool-use models |
| `deepseek` | DeepSeek | `https://api.deepseek.com/v1` | `DEEPSEEK_API_KEY` | 2 | DeepSeek-V3 (chat) + R1 (reasoning); extremely cost-effective |
| `meta-llama` | Meta Llama | `https://api.llama.com/v1` | `LLAMA_API_KEY` | 4 | Official Meta Llama API — direct access to Llama 3.x |
| `meta-llama` | Meta Llama | `https://api.llama.com/v1` | `LLAMA_API_KEY` | 3 | Official Meta Llama API — Llama 4 Maverick / Scout + Guard 4 |
| `perplexity` | Perplexity AI | `https://api.perplexity.ai` | `PERPLEXITY_API_KEY` | 4 | Sonar family with live web search built in |
### Fast Inference / Compute Clouds
@@ -27,11 +27,11 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
| ID | Display Name | Base URL | API Key Env | Models | Description |
|----|-------------|----------|-------------|--------|-------------|
| `groq` | Groq | `https://api.groq.com/openai/v1` | `GROQ_API_KEY` | 3 | GroqChip hardware; ~10× faster than GPU inference for supported models |
| `cerebras` | Cerebras | `https://api.cerebras.ai/v1` | `CEREBRAS_API_KEY` | 4 | Wafer-scale chip inference; best-in-class throughput for Llama |
| `cerebras` | Cerebras | `https://api.cerebras.ai/v1` | `CEREBRAS_API_KEY` | 3 | Wafer-scale chip inference; best-in-class throughput for Llama |
| `sambanova` | SambaNova | `https://api.sambanova.ai/v1` | `SAMBANOVA_API_KEY` | 3 | Reconfigurable Dataflow Unit (RDU) inference; fast Llama variants |
| `fireworks` | Fireworks AI | `https://api.fireworks.ai/inference/v1` | `FIREWORKS_API_KEY` | 5 | Serverless open-model hosting; fast cold-start |
| `together` | Together AI | `https://api.together.xyz/v1` | `TOGETHER_API_KEY` | 8 | Open-model hosting (Llama, Qwen, Mistral) + fine-tuning API |
| `nvidia-nim` | NVIDIA NIM | `https://integrate.api.nvidia.com/v1` | `NVIDIA_API_KEY` | 26 | NVIDIA NIM microservices; largest model selection in registry |
| `fireworks` | Fireworks AI | `https://api.fireworks.ai/inference/v1` | `FIREWORKS_API_KEY` | 3 | Serverless open-model hosting; fast cold-start |
| `together` | Together AI | `https://api.together.xyz/v1` | `TOGETHER_API_KEY` | 4 | Open-model hosting (Llama 4, DeepSeek) + fine-tuning API |
| `nvidia-nim` | NVIDIA NIM | `https://integrate.api.nvidia.com/v1` | `NVIDIA_API_KEY` | 14 | NVIDIA NIM microservices; broad open-model selection |
| `replicate` | Replicate | `https://api.replicate.com/v1` | `REPLICATE_API_TOKEN` | 3 | Run any model as a serverless API; image + video + LLM |
| `huggingface` | Hugging Face | `https://api-inference.huggingface.co/v1` | `HF_API_KEY` | 3 | HF Serverless Inference API for hosted open models |
@@ -39,15 +39,15 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
| ID | Display Name | Base URL | API Key Env | Models | Description |
|----|-------------|----------|-------------|--------|-------------|
| `bedrock` | AWS Bedrock | `https://bedrock-runtime.us-east-1.amazonaws.com` | `AWS_ACCESS_KEY_ID` | 11 | AWS-managed models (Claude, Llama, Mistral, Nova); IAM auth |
| `vertex-ai` | Google Cloud Vertex AI | `https://us-central1-aiplatform.googleapis.com` | `GOOGLE_APPLICATION_CREDENTIALS` | 6 | GCP-hosted Gemini + third-party models; service account JSON auth |
| `bedrock` | AWS Bedrock | `https://bedrock-runtime.us-east-1.amazonaws.com` | `AWS_ACCESS_KEY_ID` | 8 | AWS-managed models (Claude, Llama, Mistral, Nova); IAM auth |
| `vertex-ai` | Google Cloud Vertex AI | `https://us-central1-aiplatform.googleapis.com` | `GOOGLE_APPLICATION_CREDENTIALS` | 4 | GCP-hosted Gemini + third-party models; service account JSON auth |
| `github-copilot` | GitHub Copilot | `https://api.githubcopilot.com` | `GITHUB_TOKEN` | 1 | Uses `ApiFormat::Copilot` — proprietary protocol, not OpenAI-compatible; requires GitHub PAT with Copilot access |
### Aggregators / Routers
| ID | Display Name | Base URL | API Key Env | Models | Description |
|----|-------------|----------|-------------|--------|-------------|
| `openrouter` | OpenRouter | `https://openrouter.ai/api/v1` | `OPENROUTER_API_KEY` | 18+ | Meta-provider routing to 300+ models; also receives models from OpenRouter-only providers via sync script |
| `openrouter` | OpenRouter | `https://openrouter.ai/api/v1` | `OPENROUTER_API_KEY` | 38+ | Meta-provider routing to 300+ models; also receives models from OpenRouter-only providers via sync script |
| `siliconflow` | SiliconFlow | `https://api.siliconflow.cn/v1` | `SILICONFLOW_API_KEY` | dynamic | 硅基流动 — Chinese open-model hosting; models discovered at runtime, not hardcoded in TOML |
### Chinese Providers
@@ -55,15 +55,15 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
| ID | Display Name | Base URL | API Key Env | Models | Description |
|----|-------------|----------|-------------|--------|-------------|
| `qwen` | Qwen (Alibaba) | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `DASHSCOPE_API_KEY` | 9 | Qwen3 family by Alibaba; multi-region support (`intl` / `us`) via `[provider.regions]` |
| `moonshot` | Moonshot (Kimi) | `https://api.moonshot.ai/v1` | `MOONSHOT_API_KEY` | 5 | Kimi general chat models (moonshot-v1-8k/32k/128k) |
| `minimax` | MiniMax | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` | 8 | MiniMax M-series; strong Chinese + multilingual models |
| `zhipu` | Zhipu AI (GLM) | `https://open.bigmodel.cn/api/paas/v4` | `ZHIPU_API_KEY` | 6 | GLM-4 family by Zhipu AI (智谱); general chat + vision |
| `moonshot` | Moonshot (Kimi) | `https://api.moonshot.ai/v1` | `MOONSHOT_API_KEY` | 2 | Kimi K2 / K2.5 |
| `minimax` | MiniMax | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` | 4 | MiniMax M-series; strong Chinese + multilingual models |
| `zhipu` | Zhipu AI (GLM) | `https://open.bigmodel.cn/api/paas/v4` | `ZHIPU_API_KEY` | 2 | GLM-4.7 / GLM-5 by Zhipu AI (智谱) |
| `zai` | Z.AI | `https://api.z.ai/api/paas/v4` | `ZHIPU_API_KEY` | 2 | Z.AI general models; shares API key with zhipu |
| `baichuan` | Baichuan (百川) | `https://api.baichuan-ai.com/v1` | `BAICHUAN_API_KEY` | 2 | Baichuan4 family; strong Chinese-language performance |
| `volcengine` | Volcano Engine (Doubao) | `https://ark.cn-beijing.volces.com/api/v3` | `VOLCENGINE_API_KEY` | 8 | ByteDance Doubao models; Ark platform |
| `stepfun` | Stepfun (阶跃星辰) | `https://api.stepfun.com/v1` | `STEPFUN_API_KEY` | 4 | Step-2 family; strong long-context and reasoning |
| `baichuan` | Baichuan (百川) | `https://api.baichuan-ai.com/v1` | `BAICHUAN_API_KEY` | 1 | Baichuan4; strong Chinese-language performance |
| `volcengine` | Volcano Engine (Doubao) | `https://ark.cn-beijing.volces.com/api/v3` | `VOLCENGINE_API_KEY` | 5 | ByteDance Doubao 2.0 + UI-TARS; Ark platform |
| `stepfun` | Stepfun (阶跃星辰) | `https://api.stepfun.com/v1` | `STEPFUN_API_KEY` | 2 | Step-3 / Step-3.5 Flash; long-context reasoning |
| `tencent` | Tencent | `https://api.hunyuan.cloud.tencent.com/v1` | `HUNYUAN_API_KEY` | 1 | Hunyuan models by Tencent |
| `qianfan` | Baidu Qianfan | `https://qianfan.baidubce.com/v2` | `QIANFAN_API_KEY` | 3 | ERNIE family by Baidu; Qianfan platform |
| `qianfan` | Baidu Qianfan | `https://qianfan.baidubce.com/v2` | `QIANFAN_API_KEY` | 1 | ERNIE 4.5 by Baidu; Qianfan platform |
### Coding-Specific Endpoints
@@ -72,7 +72,7 @@ Separate `base_url` for coding workloads — not just model aliases. Same API ke
| ID | Display Name | Base URL | API Key Env | Models | vs. General |
|----|-------------|----------|-------------|--------|-------------|
| `kimi_coding` | Kimi for Code | `https://api.kimi.com/coding` | `KIMI_API_KEY` | 1 | vs `moonshot`: `api.moonshot.ai/v1` |
| `alibaba-coding-plan` | Alibaba Coding Plan (Intl) | `https://coding-intl.dashscope.aliyuncs.com/v1` | `ALIBABA_CODING_PLAN_API_KEY` | 9 | vs `qwen`: `dashscope.aliyuncs.com`; aggregates models from multiple vendors (MiniMax, GLM, Kimi) |
| `alibaba-coding-plan` | Alibaba Coding Plan (Intl) | `https://coding-intl.dashscope.aliyuncs.com/v1` | `ALIBABA_CODING_PLAN_API_KEY` | 5 | vs `qwen`: `dashscope.aliyuncs.com`; aggregates Qwen + GLM under one plan |
| `volcengine_coding` | Volcano Engine Coding Plan | `https://ark.cn-beijing.volces.com/api/coding/v3` | `VOLCENGINE_API_KEY` | dynamic | vs `volcengine`: `/api/v3`; models discovered at runtime |
| `zhipu_coding` | Zhipu Coding (CodeGeeX) | `https://open.bigmodel.cn/api/coding/paas/v4` | `ZHIPU_API_KEY` | 1 | vs `zhipu`: `/api/paas/v4`; CodeGeeX-4 coding model |
| `zai_coding` | Z.AI Coding | `https://api.z.ai/api/coding/paas/v4` | `ZHIPU_API_KEY` | 2 | vs `zai`: `/api/paas/v4`; GLM coding variants |
@@ -86,7 +86,7 @@ Route through a locally-installed CLI tool. `key_required = false`, `base_url` i
| `claude-code` | Claude Code | `claude` | 3 | `ClaudeCode` | Anthropic's official CLI; routes through Claude API with OAuth |
| `codex-cli` | Codex CLI | `codex` | 6 | `CodexCli` | OpenAI Codex CLI; also serves as fallback for `openai` provider |
| `gemini-cli` | Gemini CLI | `gemini` | 2 | `GeminiCli` | Google Gemini CLI; also serves as fallback for `gemini` provider |
| `qwen-code` | Qwen Code | `qwen-code` | 3 | `QwenCode` | Alibaba Qwen coding CLI |
| `qwen-code` | Qwen Code | `qwen-code` | 2 | `QwenCode` | Alibaba Qwen coding CLI |
### Local / Self-Hosted
providers/aion-labs.toml
-20
View File
@@ -7,26 +7,6 @@ api_key_env = "AION_LABS_API_KEY"
base_url = "https://api.aionlabs.ai/v1"
key_required = true
[[models]]
id = "aion-1.0"
display_name = "AionLabs: Aion-1.0"
tier = "frontier"
context_window = 131072
max_output_tokens = 32768
input_cost_per_m = 4.0
output_cost_per_m = 8.0
supports_streaming = true
[[models]]
id = "aion-1.0-mini"
display_name = "AionLabs: Aion-1.0-Mini"
tier = "smart"
context_window = 131072
max_output_tokens = 32768
input_cost_per_m = 0.7
output_cost_per_m = 1.4
supports_streaming = true
[[models]]
id = "aion-2.0"
display_name = "AionLabs: Aion-2.0"
providers/alibaba-coding-plan.toml
+1 -56
View File
@@ -1,5 +1,5 @@
# Alibaba Coding Plan — https://www.alibabacloud.com/help/en/model-studio/coding-plan
# Models: 8 (Pro plan: $50/month with quota-based access)
# Models: 5 (Pro plan: $50/month with quota-based access)
# Note: Monthly subscription for AI coding tools. Uses plan-specific API key (sk-sp-xxxxx)
# and dedicated base URL (https://coding-intl.dashscope.aliyuncs.com/v1)
@@ -24,34 +24,6 @@ supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "alibaba-coding-plan/qwen3.5-plus"
display_name = "Qwen 3.5 Plus"
tier = "smart"
context_window = 1000000
max_output_tokens = 65536
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "alibaba-coding-plan/qwen3-max-2026-01-23"
display_name = "Qwen 3 Max (2026-01-23)"
tier = "frontier"
context_window = 262144
max_output_tokens = 65536
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = false
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "alibaba-coding-plan/qwen3-coder-next"
display_name = "Qwen 3 Coder Next"
@@ -80,19 +52,6 @@ supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "alibaba-coding-plan/MiniMax-M2.5"
display_name = "MiniMax M2.5"
tier = "balanced"
context_window = 196608
max_output_tokens = 32768
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "alibaba-coding-plan/glm-5"
display_name = "GLM 5"
@@ -118,17 +77,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "alibaba-coding-plan/kimi-k2.5"
display_name = "Kimi K2.5"
tier = "smart"
context_window = 262144
max_output_tokens = 32768
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
providers/anthropic.toml
+1 -29
View File
@@ -1,5 +1,5 @@
# Anthropic — https://anthropic.com
# Models: 7
# Models: 5
[provider]
id = "anthropic"
@@ -56,34 +56,6 @@ supports_streaming = true
supports_thinking = true
aliases = ["sonnet", "claude-sonnet"]
[[models]]
id = "claude-opus-4-20250514"
display_name = "Claude Opus 4"
tier = "frontier"
context_window = 200000
max_output_tokens = 32000
input_cost_per_m = 15.0
output_cost_per_m = 75.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "claude-sonnet-4-20250514"
display_name = "Claude Sonnet 4"
tier = "smart"
context_window = 200000
max_output_tokens = 64000
input_cost_per_m = 3.0
output_cost_per_m = 15.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "claude-haiku-4-5-20251001"
display_name = "Claude Haiku 4.5"
providers/baichuan.toml
+1 -14
View File
@@ -1,5 +1,5 @@
# Baichuan (百川智能) — https://platform.baichuan-ai.com
# Models: 2
# Models: 1
[provider]
id = "baichuan"
@@ -20,16 +20,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["baichuan-4", "baichuan4"]
[[models]]
id = "Baichuan3-Turbo-128k"
display_name = "Baichuan-3 Turbo 128K"
tier = "smart"
context_window = 131072
max_output_tokens = 8192
input_cost_per_m = 7.15
output_cost_per_m = 7.15
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["baichuan-3-turbo", "baichuan3-turbo"]
providers/bedrock.toml
-41
View File
@@ -36,34 +36,6 @@ supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "bedrock/anthropic.claude-opus-4-20250514"
display_name = "Claude Opus 4 (Bedrock)"
tier = "frontier"
context_window = 200000
max_output_tokens = 32000
input_cost_per_m = 15.00
output_cost_per_m = 75.00
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "bedrock/anthropic.claude-sonnet-4-20250514"
display_name = "Claude Sonnet 4 (Bedrock)"
tier = "smart"
context_window = 200000
max_output_tokens = 64000
input_cost_per_m = 3.00
output_cost_per_m = 15.00
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "bedrock/anthropic.claude-haiku-4-5-20251001"
display_name = "Claude Haiku 4.5 (Bedrock)"
@@ -91,19 +63,6 @@ supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "bedrock/amazon.nova-lite-v1:0"
display_name = "Amazon Nova Lite (Bedrock)"
tier = "fast"
context_window = 300000
max_output_tokens = 5120
input_cost_per_m = 0.06
output_cost_per_m = 0.24
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "bedrock/meta.llama3-3-70b-instruct-v1:0"
display_name = "Llama 3.3 70B (Bedrock)"
providers/cerebras.toml
+1 -14
View File
@@ -1,5 +1,5 @@
# Cerebras — https://cerebras.ai
# Models: 4
# Models: 3
[provider]
id = "cerebras"
@@ -21,19 +21,6 @@ supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "cerebras/llama3.1-8b"
display_name = "Llama 3.1 8B (Cerebras)"
tier = "fast"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.01
output_cost_per_m = 0.01
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "cerebras/llama-4-scout-17b"
display_name = "Llama 4 Scout (Cerebras)"
providers/cohere.toml
+1 -27
View File
@@ -1,5 +1,5 @@
# Cohere — https://cohere.com
# Models: 4
# Models: 2
[provider]
id = "cohere"
@@ -21,19 +21,6 @@ supports_vision = false
supports_streaming = true
aliases = ["command-r"]
[[models]]
id = "command-r-08-2024"
display_name = "Command R (Aug 2024)"
tier = "balanced"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.15
output_cost_per_m = 0.60
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "command-a"
display_name = "Command A"
@@ -46,16 +33,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["command"]
[[models]]
id = "command-light"
display_name = "Command Light"
tier = "fast"
context_window = 4096
max_output_tokens = 4096
input_cost_per_m = 0.30
output_cost_per_m = 0.60
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
providers/deepinfra.toml
-48
View File
@@ -8,54 +8,6 @@ api_key_env = "DEEPINFRA_API_KEY"
base_url = "https://api.deepinfra.com/v1/openai"
key_required = true
[[models]]
id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
display_name = "Llama 3.1 8B Instruct"
tier = "fast"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.06
output_cost_per_m = 0.06
supports_tools = true
supports_vision = false
supports_streaming = true
[[models]]
id = "meta-llama/Meta-Llama-3.1-70B-Instruct"
display_name = "Llama 3.1 70B Instruct"
tier = "balanced"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.35
output_cost_per_m = 0.4
supports_tools = true
supports_vision = false
supports_streaming = true
[[models]]
id = "meta-llama/Meta-Llama-3.1-405B-Instruct"
display_name = "Llama 3.1 405B Instruct"
tier = "smart"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.8
output_cost_per_m = 0.8
supports_tools = true
supports_vision = false
supports_streaming = true
[[models]]
id = "mistralai/Mistral-7B-Instruct-v0.3"
display_name = "Mistral 7B Instruct v0.3"
tier = "fast"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 0.07
output_cost_per_m = 0.07
supports_tools = true
supports_vision = false
supports_streaming = true
[[models]]
id = "Qwen/Qwen2.5-72B-Instruct"
display_name = "Qwen 2.5 72B Instruct"
providers/fireworks.toml
+1 -27
View File
@@ -1,5 +1,5 @@
# Fireworks AI — https://fireworks.ai
# Models: 5
# Models: 3
[provider]
id = "fireworks"
@@ -8,19 +8,6 @@ api_key_env = "FIREWORKS_API_KEY"
base_url = "https://api.fireworks.ai/inference/v1"
key_required = true
[[models]]
id = "accounts/fireworks/models/llama-v3p1-405b-instruct"
display_name = "Llama 3.1 405B (Fireworks)"
tier = "frontier"
context_window = 131072
max_output_tokens = 16384
input_cost_per_m = 3.00
output_cost_per_m = 3.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "accounts/fireworks/models/llama-v3p3-70b-instruct"
display_name = "Llama 3.3 70B (Fireworks)"
@@ -60,16 +47,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "accounts/fireworks/models/mixtral-8x22b-instruct"
display_name = "Mixtral 8x22B (Fireworks)"
tier = "balanced"
context_window = 65536
max_output_tokens = 4096
input_cost_per_m = 0.90
output_cost_per_m = 0.90
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
providers/meta-llama.toml
+1 -11
View File
@@ -1,5 +1,5 @@
# meta-llama — https://llama.com
# Models: 5
# Models: 3
[provider]
id = "meta-llama"
@@ -28,16 +28,6 @@ input_cost_per_m = 0.08
output_cost_per_m = 0.3
supports_streaming = true
[[models]]
id = "llama-3.3-70b-instruct"
display_name = "Meta: Llama 3.3 70B Instruct"
tier = "fast"
context_window = 131072
max_output_tokens = 16384
input_cost_per_m = 0.1
output_cost_per_m = 0.32
supports_streaming = true
[[models]]
id = "llama-guard-4-12b"
display_name = "Meta: Llama Guard 4 12B"
providers/minimax.toml
+1 -53
View File
@@ -1,5 +1,5 @@
# MiniMax — https://minimax.io
# Models: 8
# Models: 4
# Regions: international (default), china (minimaxi.com)
[provider]
@@ -45,19 +45,6 @@ supports_vision = false
supports_streaming = true
aliases = ["minimax-m2.7-highspeed", "m2.7-highspeed"]
[[models]]
id = "minimax-text-01"
display_name = "MiniMax Text 01"
tier = "smart"
context_window = 1048576
max_output_tokens = 16384
input_cost_per_m = 1.00
output_cost_per_m = 3.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["minimax"]
[[models]]
id = "MiniMax-M2.5"
display_name = "MiniMax M2.5"
@@ -83,42 +70,3 @@ supports_tools = true
supports_vision = true
supports_streaming = true
aliases = ["minimax-m2.5-highspeed", "m2.5-highspeed"]
[[models]]
id = "MiniMax-M2.1"
display_name = "MiniMax M2.1"
tier = "smart"
context_window = 1048576
max_output_tokens = 16384
input_cost_per_m = 1.00
output_cost_per_m = 3.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["minimax-m2.1"]
[[models]]
id = "abab6.5-chat"
display_name = "ABAB 6.5 Chat"
tier = "balanced"
context_window = 245760
max_output_tokens = 8192
input_cost_per_m = 0.50
output_cost_per_m = 1.50
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "abab7-chat"
display_name = "ABAB 7 Chat"
tier = "smart"
context_window = 524288
max_output_tokens = 16384
input_cost_per_m = 0.80
output_cost_per_m = 2.40
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = ["abab7"]
providers/moonshot.toml
+1 -40
View File
@@ -1,5 +1,5 @@
# Moonshot / Kimi — https://moonshot.ai
# Models: 5
# Models: 2
[provider]
id = "moonshot"
@@ -8,45 +8,6 @@ api_key_env = "MOONSHOT_API_KEY"
base_url = "https://api.moonshot.ai/v1"
key_required = true
[[models]]
id = "moonshot-v1-128k"
display_name = "Moonshot V1 128K"
tier = "smart"
context_window = 131072
max_output_tokens = 8192
input_cost_per_m = 2.00
output_cost_per_m = 5.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["moonshot"]
[[models]]
id = "moonshot-v1-32k"
display_name = "Moonshot V1 32K"
tier = "balanced"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 1.00
output_cost_per_m = 3.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "moonshot-v1-8k"
display_name = "Moonshot V1 8K"
tier = "fast"
context_window = 8192
max_output_tokens = 4096
input_cost_per_m = 0.20
output_cost_per_m = 2.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "kimi-k2"
display_name = "Kimi K2"
providers/nvidia-nim.toml
+1 -159
View File
@@ -1,5 +1,5 @@
# NVIDIA NIM — https://build.nvidia.com
# Models: 22
# Models: 14
[provider]
id = "nvidia-nim"
@@ -36,32 +36,6 @@ supports_vision = false
supports_streaming = true
aliases = ["nemotron-super"]
[[models]]
id = "nvidia/llama-3.1-nemotron-70b-instruct"
display_name = "Nemotron 70B"
tier = "balanced"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 1.2
output_cost_per_m = 1.2
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["nemotron-70b"]
[[models]]
id = "nvidia/nemotron-mini-4b-instruct"
display_name = "Nemotron Mini 4B"
tier = "fast"
context_window = 4096
max_output_tokens = 4096
input_cost_per_m = 0.01
output_cost_per_m = 0.01
supports_tools = false
supports_vision = false
supports_streaming = true
aliases = ["nemotron-mini"]
# ── Meta Llama models ────────────────────────────────────────────
[[models]]
@@ -103,58 +77,6 @@ supports_vision = false
supports_streaming = true
aliases = ["llama-70b"]
[[models]]
id = "meta/llama-3.1-405b-instruct"
display_name = "Llama 3.1 405B"
tier = "frontier"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 2.00
output_cost_per_m = 2.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["llama-405b"]
[[models]]
id = "meta/llama-3.1-8b-instruct"
display_name = "Llama 3.1 8B"
tier = "fast"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.03
output_cost_per_m = 0.03
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "meta/llama-3.2-90b-vision-instruct"
display_name = "Llama 3.2 90B Vision"
tier = "smart"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.35
output_cost_per_m = 0.40
supports_tools = false
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "meta/llama-3.2-11b-vision-instruct"
display_name = "Llama 3.2 11B Vision"
tier = "balanced"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.07
output_cost_per_m = 0.07
supports_tools = false
supports_vision = true
supports_streaming = true
aliases = []
# ── Mistral models ───────────────────────────────────────────────
[[models]]
@@ -170,32 +92,6 @@ supports_vision = false
supports_streaming = true
aliases = ["mistral-large-3"]
[[models]]
id = "mistralai/mistral-small-3.1-24b-instruct-2503"
display_name = "Mistral Small 3.1 24B"
tier = "balanced"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.10
output_cost_per_m = 0.30
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["mistral-small"]
[[models]]
id = "mistralai/mixtral-8x22b-instruct-v0.1"
display_name = "Mixtral 8x22B"
tier = "balanced"
context_window = 65536
max_output_tokens = 4096
input_cost_per_m = 0.27
output_cost_per_m = 0.27
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["mixtral"]
# ── DeepSeek models ──────────────────────────────────────────────
[[models]]
@@ -211,20 +107,6 @@ supports_vision = false
supports_streaming = true
aliases = ["deepseek-v3"]
[[models]]
id = "deepseek-ai/deepseek-r1-distill-qwen-32b"
display_name = "DeepSeek R1 Distill 32B"
tier = "balanced"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.10
output_cost_per_m = 0.10
supports_tools = false
supports_vision = false
supports_streaming = true
supports_thinking = true
aliases = ["deepseek-r1-32b"]
# ── Qwen models ──────────────────────────────────────────────────
[[models]]
@@ -241,33 +123,6 @@ supports_streaming = true
supports_thinking = true
aliases = ["qwen3.5"]
[[models]]
id = "qwen/qwen2.5-coder-32b-instruct"
display_name = "Qwen 2.5 Coder 32B"
tier = "balanced"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.10
output_cost_per_m = 0.10
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["qwen-coder"]
[[models]]
id = "qwen/qwq-32b"
display_name = "QWQ 32B"
tier = "balanced"
context_window = 128000
max_output_tokens = 16384
input_cost_per_m = 0.15
output_cost_per_m = 0.58
supports_tools = false
supports_vision = false
supports_streaming = true
supports_thinking = true
aliases = []
# ── Google Gemma models ──────────────────────────────────────────
[[models]]
@@ -298,19 +153,6 @@ supports_vision = true
supports_streaming = true
aliases = ["phi-4"]
[[models]]
id = "microsoft/phi-4-mini-instruct"
display_name = "Phi-4 Mini"
tier = "fast"
context_window = 16384
max_output_tokens = 4096
input_cost_per_m = 0.03
output_cost_per_m = 0.03
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["phi-4-mini"]
[[models]]
id = "nvidia/nemotron-3-nano-30b-a3b"
display_name = "Nvidia: Nemotron 3 Nano 30B"
providers/openai.toml
-67
View File
@@ -9,73 +9,6 @@ base_url = "https://api.openai.com/v1"
key_required = true
media_capabilities = ["image_generation", "text_to_speech"]
[[models]]
id = "gpt-4.1"
display_name = "GPT-4.1"
tier = "frontier"
context_window = 1047576
max_output_tokens = 32768
input_cost_per_m = 2.00
output_cost_per_m = 8.00
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "gpt-4.1-mini"
display_name = "GPT-4.1 Mini"
tier = "balanced"
context_window = 1047576
max_output_tokens = 32768
input_cost_per_m = 0.40
output_cost_per_m = 1.60
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "gpt-4.1-nano"
display_name = "GPT-4.1 Nano"
tier = "fast"
context_window = 1047576
max_output_tokens = 32768
input_cost_per_m = 0.10
output_cost_per_m = 0.40
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "o3"
display_name = "o3"
tier = "frontier"
context_window = 200000
max_output_tokens = 100000
input_cost_per_m = 2.0
output_cost_per_m = 8.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "o4-mini"
display_name = "o4-mini"
tier = "smart"
context_window = 200000
max_output_tokens = 100000
input_cost_per_m = 1.1
output_cost_per_m = 4.4
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "gpt-5"
display_name = "GPT-5"
providers/openrouter.toml
+1 -160
View File
@@ -1,5 +1,5 @@
# OpenRouter — https://openrouter.ai
# Models: 18 (10 paid + 8 free)
# Models: 38
[provider]
id = "openrouter"
@@ -39,33 +39,6 @@ supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "openrouter/anthropic/claude-sonnet-4"
display_name = "Claude Sonnet 4 (OpenRouter)"
tier = "smart"
context_window = 200000
max_output_tokens = 64000
input_cost_per_m = 3.0
output_cost_per_m = 15.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "openrouter/openai/gpt-4o"
display_name = "GPT-4o (OpenRouter)"
tier = "smart"
context_window = 128000
max_output_tokens = 16384
input_cost_per_m = 2.5
output_cost_per_m = 10.0
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/deepseek/deepseek-chat"
display_name = "DeepSeek V3 (OpenRouter)"
@@ -79,32 +52,6 @@ supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/meta-llama/llama-3.3-70b-instruct"
display_name = "Llama 3.3 70B (OpenRouter)"
tier = "balanced"
context_window = 128000
max_output_tokens = 32768
input_cost_per_m = 0.39
output_cost_per_m = 0.39
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/qwen/qwen-2.5-72b-instruct"
display_name = "Qwen 2.5 72B (OpenRouter)"
tier = "balanced"
context_window = 128000
max_output_tokens = 32768
input_cost_per_m = 0.36
output_cost_per_m = 0.36
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/google/gemini-2.5-pro"
display_name = "Gemini 2.5 Pro (OpenRouter)"
@@ -132,19 +79,6 @@ supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/google/gemma-2-9b-it"
display_name = "Gemma 2 9B (OpenRouter)"
tier = "fast"
context_window = 8192
max_output_tokens = 4096
input_cost_per_m = 0.03
output_cost_per_m = 0.09
supports_tools = false
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/deepseek/deepseek-r1"
display_name = "DeepSeek R1 (OpenRouter)"
@@ -244,19 +178,6 @@ supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/meta-llama/llama-3.2-3b-instruct:free"
display_name = "Llama 3.2 3B Free (OpenRouter)"
tier = "fast"
context_window = 131072
max_output_tokens = 4096
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = false
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "openrouter/ai21/jamba-large-1.7"
display_name = "AI21: Jamba Large 1.7 (OpenRouter)"
@@ -277,16 +198,6 @@ input_cost_per_m = 0.09
output_cost_per_m = 0.45
supports_streaming = true
[[models]]
id = "openrouter/allenai/olmo-3-32b-think"
display_name = "AllenAI: Olmo 3 32B Think (OpenRouter)"
tier = "fast"
context_window = 65536
max_output_tokens = 65536
input_cost_per_m = 0.15
output_cost_per_m = 0.5
supports_streaming = true
[[models]]
id = "openrouter/allenai/olmo-3.1-32b-instruct"
display_name = "AllenAI: Olmo 3.1 32B Instruct (OpenRouter)"
@@ -307,16 +218,6 @@ input_cost_per_m = 0.3
output_cost_per_m = 2.5
supports_streaming = true
[[models]]
id = "openrouter/amazon/nova-lite-v1"
display_name = "Amazon: Nova Lite 1.0 (OpenRouter)"
tier = "fast"
context_window = 300000
max_output_tokens = 5120
input_cost_per_m = 0.06
output_cost_per_m = 0.24
supports_streaming = true
[[models]]
id = "openrouter/amazon/nova-micro-v1"
display_name = "Amazon: Nova Micro 1.0 (OpenRouter)"
@@ -417,16 +318,6 @@ input_cost_per_m = 2.5
output_cost_per_m = 10.0
supports_streaming = true
[[models]]
id = "openrouter/liquid/lfm-2-24b-a2b"
display_name = "LiquidAI: LFM2-24B-A2B (OpenRouter)"
tier = "fast"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 0.03
output_cost_per_m = 0.12
supports_streaming = true
[[models]]
id = "openrouter/liquid/lfm-2.5-1.2b-instruct:free"
display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free) (OpenRouter)"
@@ -457,46 +348,6 @@ input_cost_per_m = 0.135
output_cost_per_m = 0.5
supports_streaming = true
[[models]]
id = "openrouter/nousresearch/hermes-2-pro-llama-3-8b"
display_name = "NousResearch: Hermes 2 Pro - Llama-3 8B (OpenRouter)"
tier = "fast"
context_window = 8192
max_output_tokens = 8192
input_cost_per_m = 0.14
output_cost_per_m = 0.14
supports_streaming = true
[[models]]
id = "openrouter/nousresearch/hermes-3-llama-3.1-405b"
display_name = "Nous: Hermes 3 405B Instruct (OpenRouter)"
tier = "smart"
context_window = 131072
max_output_tokens = 16384
input_cost_per_m = 1.0
output_cost_per_m = 1.0
supports_streaming = true
[[models]]
id = "openrouter/nousresearch/hermes-3-llama-3.1-405b:free"
display_name = "Nous: Hermes 3 405B Instruct (free) (OpenRouter)"
tier = "fast"
context_window = 131072
max_output_tokens = 16384
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_streaming = true
[[models]]
id = "openrouter/nousresearch/hermes-3-llama-3.1-70b"
display_name = "Nous: Hermes 3 70B Instruct (OpenRouter)"
tier = "fast"
context_window = 131072
max_output_tokens = 16384
input_cost_per_m = 0.3
output_cost_per_m = 0.3
supports_streaming = true
[[models]]
id = "openrouter/nousresearch/hermes-4-405b"
display_name = "Nous: Hermes 4 405B (OpenRouter)"
@@ -527,16 +378,6 @@ input_cost_per_m = 0.2
output_cost_per_m = 1.1
supports_streaming = true
[[models]]
id = "openrouter/rekaai/reka-edge"
display_name = "Reka Edge (OpenRouter)"
tier = "fast"
context_window = 16384
max_output_tokens = 16384
input_cost_per_m = 0.1
output_cost_per_m = 0.1
supports_streaming = true
[[models]]
id = "openrouter/rekaai/reka-flash-3"
display_name = "Reka Flash 3 (OpenRouter)"
providers/qianfan.toml
+1 -27
View File
@@ -1,5 +1,5 @@
# Baidu Qianfan / ERNIE — https://qianfan.baidubce.com
# Models: 3
# Models: 1
[provider]
id = "qianfan"
@@ -20,29 +20,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["ernie"]
[[models]]
id = "ernie-4.0-turbo-8k"
display_name = "ERNIE 4.0 Turbo 8K"
tier = "balanced"
context_window = 8192
max_output_tokens = 4096
input_cost_per_m = 1.00
output_cost_per_m = 3.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "ernie-speed-128k"
display_name = "ERNIE Speed 128K"
tier = "fast"
context_window = 131072
max_output_tokens = 4096
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
providers/qwen-code.toml
+1 -15
View File
@@ -1,5 +1,5 @@
# Qwen Code CLI
# Models: 3
# Models: 2
[provider]
id = "qwen-code"
@@ -34,17 +34,3 @@ supports_tools = false
supports_vision = false
supports_streaming = true
aliases = ["qwen-code-coder-plus"]
[[models]]
id = "qwen-code/qwq-32b"
display_name = "QwQ 32B (CLI)"
tier = "balanced"
context_window = 131072
max_output_tokens = 8192
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = false
supports_vision = false
supports_streaming = true
supports_thinking = true
aliases = ["qwen-code-qwq"]
providers/stepfun.toml
+1 -28
View File
@@ -1,5 +1,5 @@
# Stepfun (阶跃星辰) — https://platform.stepfun.com
# Models: 4
# Models: 2
[provider]
id = "stepfun"
@@ -33,30 +33,3 @@ supports_tools = true
supports_vision = true
supports_streaming = true
aliases = ["stepfun-3"]
[[models]]
id = "step-2-mini"
display_name = "Step 2 Mini"
tier = "fast"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 0.14
output_cost_per_m = 0.29
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["stepfun-mini"]
[[models]]
id = "step-1o-turbo-vision"
display_name = "Step 1o Turbo Vision"
tier = "smart"
context_window = 32768
max_output_tokens = 8192
input_cost_per_m = 0.36
output_cost_per_m = 1.14
supports_tools = false
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = ["stepfun-vision"]
providers/together.toml
+1 -53
View File
@@ -1,5 +1,5 @@
# Together AI — https://together.ai
# Models: 8
# Models: 4
[provider]
id = "together"
@@ -8,32 +8,6 @@ api_key_env = "TOGETHER_API_KEY"
base_url = "https://api.together.xyz/v1"
key_required = true
[[models]]
id = "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
display_name = "Llama 3.1 405B (Together)"
tier = "frontier"
context_window = 130000
max_output_tokens = 4096
input_cost_per_m = 3.50
output_cost_per_m = 3.50
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "meta-llama/Llama-3.3-70B-Instruct-Turbo"
display_name = "Llama 3.3 70B (Together)"
tier = "smart"
context_window = 128000
max_output_tokens = 4096
input_cost_per_m = 0.88
output_cost_per_m = 0.88
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
display_name = "Llama 4 Maverick (Together)"
@@ -86,29 +60,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "Qwen/Qwen2.5-72B-Instruct-Turbo"
display_name = "Qwen 2.5 72B (Together)"
tier = "smart"
context_window = 32768
max_output_tokens = 4096
input_cost_per_m = 0.20
output_cost_per_m = 0.60
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
display_name = "Mixtral 8x22B (Together)"
tier = "balanced"
context_window = 65536
max_output_tokens = 4096
input_cost_per_m = 0.60
output_cost_per_m = 0.60
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
providers/vertex-ai.toml
-28
View File
@@ -63,31 +63,3 @@ supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "vertex-ai/gemini-1.5-pro"
display_name = "Gemini 1.5 Pro (Vertex AI)"
provider = "vertex-ai"
tier = "smart"
context_window = 2097152
max_output_tokens = 8192
input_cost_per_m = 1.25
output_cost_per_m = 5.0
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "vertex-ai/gemini-1.5-flash"
display_name = "Gemini 1.5 Flash (Vertex AI)"
provider = "vertex-ai"
tier = "fast"
context_window = 1048576
max_output_tokens = 8192
input_cost_per_m = 0.075
output_cost_per_m = 0.3
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
providers/volcengine.toml
+1 -40
View File
@@ -1,5 +1,5 @@
# Volcano Engine / Doubao — https://volcengine.com
# Models: 7
# Models: 5
[provider]
id = "volcengine"
@@ -60,45 +60,6 @@ supports_vision = false
supports_streaming = true
aliases = ["doubao-code", "doubao-seed-code"]
[[models]]
id = "doubao-seed-1-8"
display_name = "Doubao Seed 1.8"
tier = "smart"
context_window = 262144
max_output_tokens = 16384
input_cost_per_m = 0.80
output_cost_per_m = 2.00
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = ["doubao-1.8", "doubao-seed-1.8"]
[[models]]
id = "doubao-seed-1-6-251015"
display_name = "Doubao Seed 1.6 Pro"
tier = "smart"
context_window = 262144
max_output_tokens = 16384
input_cost_per_m = 0.80
output_cost_per_m = 2.00
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["doubao", "doubao-1.6"]
[[models]]
id = "doubao-seed-1-6-vision-251015"
display_name = "Doubao Seed 1.6 Vision"
tier = "smart"
context_window = 262144
max_output_tokens = 16384
input_cost_per_m = 0.80
output_cost_per_m = 2.00
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = ["doubao-vision"]
[[models]]
id = "ui-tars-1.5-7b"
display_name = "ByteDance: UI-TARS 7B"
providers/xai.toml
+1 -27
View File
@@ -1,5 +1,5 @@
# xAI — https://x.ai
# Models: 7
# Models: 5
[provider]
id = "xai"
@@ -74,29 +74,3 @@ supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "grok-3"
display_name = "Grok 3"
tier = "frontier"
context_window = 131072
max_output_tokens = 32768
input_cost_per_m = 3.0
output_cost_per_m = 15.0
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = ["grok3"]
[[models]]
id = "grok-3-mini"
display_name = "Grok 3 Mini"
tier = "balanced"
context_window = 131072
max_output_tokens = 32768
input_cost_per_m = 0.30
output_cost_per_m = 0.50
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
providers/xiaomi.toml
-30
View File
@@ -7,36 +7,6 @@ api_key_env = "XIAOMI_ACCESS_KEY_ID"
base_url = "https://cnbj3-cloud-ml.api.xiaomi.net"
key_required = true
[[models]]
id = "mimo-v2-flash"
display_name = "Xiaomi: MiMo-V2-Flash"
tier = "fast"
context_window = 262144
max_output_tokens = 65536
input_cost_per_m = 0.09
output_cost_per_m = 0.29
supports_streaming = true
[[models]]
id = "mimo-v2-omni"
display_name = "Xiaomi: MiMo-V2-Omni"
tier = "fast"
context_window = 262144
max_output_tokens = 65536
input_cost_per_m = 0.4
output_cost_per_m = 2.0
supports_streaming = true
[[models]]
id = "mimo-v2-pro"
display_name = "Xiaomi: MiMo-V2-Pro"
tier = "smart"
context_window = 1048576
max_output_tokens = 131072
input_cost_per_m = 1.0
output_cost_per_m = 3.0
supports_streaming = true
[[models]]
id = "mimo-v2.5"
display_name = "Xiaomi: MiMo-V2.5"
providers/zhipu.toml
+1 -53
View File
@@ -1,5 +1,5 @@
# Zhipu AI (GLM) — https://open.bigmodel.cn
# Models: 6
# Models: 2
[provider]
id = "zhipu"
@@ -8,58 +8,6 @@ api_key_env = "ZHIPU_API_KEY"
base_url = "https://open.bigmodel.cn/api/paas/v4"
key_required = true
[[models]]
id = "glm-4-plus"
display_name = "GLM-4 Plus"
tier = "smart"
context_window = 131072
max_output_tokens = 8192
input_cost_per_m = 0.60
output_cost_per_m = 2.20
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["glm"]
[[models]]
id = "glm-4-flash"
display_name = "GLM-4 Flash"
tier = "fast"
context_window = 131072
max_output_tokens = 8192
input_cost_per_m = 0.0
output_cost_per_m = 0.0
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "glm-4v-plus"
display_name = "GLM-4V Plus"
tier = "smart"
context_window = 8192
max_output_tokens = 4096
input_cost_per_m = 0.60
output_cost_per_m = 2.20
supports_tools = true
supports_vision = true
supports_streaming = true
aliases = []
[[models]]
id = "glm-4-long"
display_name = "GLM-4 Long"
tier = "balanced"
context_window = 1000000
max_output_tokens = 8192
input_cost_per_m = 0.10
output_cost_per_m = 0.10
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = []
[[models]]
id = "glm-5-20250605"
display_name = "GLM-5"