Evan
541052dc79
* chore: prune deprecated models across providers Remove old-generation models that are strictly superseded by current versions on the same provider/family.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 * chore: second pass — prune more deprecated models Apply the same 'strictly superseded by same-provider/family successor' rule to providers missed in the first pass: - openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5) - meta-llama: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.
191 lines
4.2 KiB
TOML
191 lines
4.2 KiB
TOML
# OpenAI — https://openai.com
|
|
# Models: 18 (including 2 Codex variants + 1 image-generation model)
|
|
|
|
[provider]
|
|
id = "openai"
|
|
display_name = "OpenAI"
|
|
api_key_env = "OPENAI_API_KEY"
|
|
base_url = "https://api.openai.com/v1"
|
|
key_required = true
|
|
media_capabilities = ["image_generation", "text_to_speech"]
|
|
|
|
[[models]]
|
|
id = "gpt-5"
|
|
display_name = "GPT-5"
|
|
tier = "frontier"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 1.25
|
|
output_cost_per_m = 10.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-5-mini"
|
|
display_name = "GPT-5 Mini"
|
|
tier = "balanced"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 0.25
|
|
output_cost_per_m = 2.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["gpt5-mini"]
|
|
|
|
[[models]]
|
|
id = "gpt-5-nano"
|
|
display_name = "GPT-5 Nano"
|
|
tier = "fast"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 0.05
|
|
output_cost_per_m = 0.40
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-5.1"
|
|
display_name = "GPT-5.1"
|
|
tier = "frontier"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 1.25
|
|
output_cost_per_m = 10.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-5.2"
|
|
display_name = "GPT-5.2"
|
|
tier = "frontier"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 1.75
|
|
output_cost_per_m = 14.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["gpt5"]
|
|
|
|
[[models]]
|
|
id = "gpt-5.2-pro"
|
|
display_name = "GPT-5.2 Pro"
|
|
tier = "frontier"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 21.0
|
|
output_cost_per_m = 168.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-5.4"
|
|
display_name = "GPT-5.4"
|
|
tier = "frontier"
|
|
context_window = 1050000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 2.50
|
|
output_cost_per_m = 15.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-5.4-mini"
|
|
display_name = "GPT-5.4 Mini"
|
|
tier = "balanced"
|
|
context_window = 400000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 0.75
|
|
output_cost_per_m = 4.50
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
# GPT-5.5 — released 2026-04-23.
|
|
# Source: https://openai.com/index/introducing-gpt-5-5/
|
|
# API availability announced as "very soon" at publication; pricing confirmed.
|
|
[[models]]
|
|
id = "gpt-5.5"
|
|
display_name = "GPT-5.5"
|
|
tier = "frontier"
|
|
context_window = 1000000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 5.00
|
|
output_cost_per_m = 30.00
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-5.5-pro"
|
|
display_name = "GPT-5.5 Pro"
|
|
tier = "frontier"
|
|
context_window = 1000000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 30.00
|
|
output_cost_per_m = 180.00
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
# Codex variants (same OpenAI driver & API key)
|
|
|
|
[[models]]
|
|
id = "codex/gpt-4.1"
|
|
display_name = "GPT-4.1 (Codex)"
|
|
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 = ["codex", "codex-4.1"]
|
|
|
|
[[models]]
|
|
id = "codex/o4-mini"
|
|
display_name = "o4-mini (Codex)"
|
|
tier = "smart"
|
|
context_window = 200000
|
|
max_output_tokens = 100000
|
|
input_cost_per_m = 1.10
|
|
output_cost_per_m = 4.40
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["codex-o4"]
|
|
|
|
# Image generation — priced per token (text + image), no conventional context
|
|
# window. Snapshot gpt-image-2-2026-04-21 released 2026-04-21.
|
|
# Source: https://developers.openai.com/api/docs/models/gpt-image-2
|
|
# Pricing: https://developers.openai.com/api/docs/pricing
|
|
[[models]]
|
|
id = "gpt-image-2"
|
|
display_name = "GPT Image 2"
|
|
tier = "frontier"
|
|
modality = "image"
|
|
input_cost_per_m = 5.00
|
|
output_cost_per_m = 10.00
|
|
image_input_cost_per_m = 8.00
|
|
image_output_cost_per_m = 30.00
|
|
supports_tools = false
|
|
supports_vision = true
|
|
supports_streaming = false
|
|
aliases = ["gpt-image-2-2026-04-21"]
|