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* chore: prune deprecated models across providers Remove old-generation models that are strictly superseded by current versions on the same provider/family.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 * chore: second pass — prune more deprecated models Apply the same 'strictly superseded by same-provider/family successor' rule to providers missed in the first pass: - openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5) - meta-llama: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.
196 lines
5.2 KiB
TOML
196 lines
5.2 KiB
TOML
# NVIDIA NIM — https://build.nvidia.com
|
|
# Models: 14
|
|
|
|
[provider]
|
|
id = "nvidia-nim"
|
|
display_name = "NVIDIA NIM"
|
|
api_key_env = "NVIDIA_API_KEY"
|
|
base_url = "https://integrate.api.nvidia.com/v1"
|
|
key_required = true
|
|
|
|
# ── NVIDIA models ────────────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "nvidia/llama-3.1-nemotron-ultra-253b-v1"
|
|
display_name = "Nemotron Ultra 253B"
|
|
tier = "frontier"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.6
|
|
output_cost_per_m = 1.8
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["nemotron-ultra"]
|
|
|
|
[[models]]
|
|
id = "nvidia/llama-3.3-nemotron-super-49b-v1.5"
|
|
display_name = "Nemotron Super 49B v1.5"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.40
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["nemotron-super"]
|
|
|
|
# ── Meta Llama models ────────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "meta/llama-4-maverick-17b-128e-instruct"
|
|
display_name = "Llama 4 Maverick 128E"
|
|
tier = "frontier"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.80
|
|
output_cost_per_m = 0.80
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["llama4-maverick"]
|
|
|
|
[[models]]
|
|
id = "meta/llama-4-scout-17b-16e-instruct"
|
|
display_name = "Llama 4 Scout 16E"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.40
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["llama4-scout"]
|
|
|
|
[[models]]
|
|
id = "meta/llama-3.3-70b-instruct"
|
|
display_name = "Llama 3.3 70B"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.10
|
|
output_cost_per_m = 0.10
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["llama-70b"]
|
|
|
|
# ── Mistral models ───────────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "mistralai/mistral-large-3-675b-instruct-2512"
|
|
display_name = "Mistral Large 3 675B"
|
|
tier = "frontier"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 1.50
|
|
output_cost_per_m = 4.50
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["mistral-large-3"]
|
|
|
|
# ── DeepSeek models ──────────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "deepseek-ai/deepseek-v3.2"
|
|
display_name = "DeepSeek V3.2"
|
|
tier = "frontier"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.50
|
|
output_cost_per_m = 2.00
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["deepseek-v3"]
|
|
|
|
# ── Qwen models ──────────────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "qwen/qwen3.5-397b-a17b"
|
|
display_name = "Qwen 3.5 397B MoE"
|
|
tier = "frontier"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.39
|
|
output_cost_per_m = 2.34
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["qwen3.5"]
|
|
|
|
# ── Google Gemma models ──────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "google/gemma-3-27b-it"
|
|
display_name = "Gemma 3 27B"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.08
|
|
output_cost_per_m = 0.16
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["gemma"]
|
|
|
|
# ── Microsoft Phi models ─────────────────────────────────────────
|
|
|
|
[[models]]
|
|
id = "microsoft/phi-4-multimodal-instruct"
|
|
display_name = "Phi-4 Multimodal"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.07
|
|
output_cost_per_m = 0.07
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["phi-4"]
|
|
|
|
[[models]]
|
|
id = "nvidia/nemotron-3-nano-30b-a3b"
|
|
display_name = "Nvidia: Nemotron 3 Nano 30B"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.05
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nvidia/nemotron-3-super-120b-a12b"
|
|
display_name = "Nvidia: Nemotron 3 Super 120B"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.09
|
|
output_cost_per_m = 0.45
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nvidia/nemotron-nano-12b-v2-vl"
|
|
display_name = "Nvidia: Nemotron Nano 12B V2 VL"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.2
|
|
output_cost_per_m = 0.6
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nvidia/nemotron-nano-9b-v2"
|
|
display_name = "Nvidia: Nemotron Nano 9B V2"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.04
|
|
output_cost_per_m = 0.16
|
|
supports_streaming = true
|