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* chore: prune deprecated models across providers Remove old-generation models that are strictly superseded by current versions on the same provider/family.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 * chore: second pass — prune more deprecated models Apply the same 'strictly superseded by same-provider/family successor' rule to providers missed in the first pass: - openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5) - meta-llama: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.
440 lines
11 KiB
TOML
440 lines
11 KiB
TOML
# OpenRouter — https://openrouter.ai
|
|
# Models: 38
|
|
|
|
[provider]
|
|
id = "openrouter"
|
|
display_name = "OpenRouter"
|
|
api_key_env = "OPENROUTER_API_KEY"
|
|
base_url = "https://openrouter.ai/api/v1"
|
|
key_required = true
|
|
|
|
# Default for the provider: the first [[models]] entry is returned by
|
|
# default_model_for_provider("openrouter") when no alias override is set.
|
|
|
|
[[models]]
|
|
id = "openrouter/qwen/qwen3.6-plus:free"
|
|
display_name = "Qwen 3.6 Plus Free (OpenRouter)"
|
|
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 = "openrouter/google/gemini-2.5-flash"
|
|
display_name = "Gemini 2.5 Flash (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 1048576
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.60
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "openrouter/deepseek/deepseek-chat"
|
|
display_name = "DeepSeek V3 (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.14
|
|
output_cost_per_m = 0.28
|
|
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)"
|
|
tier = "frontier"
|
|
context_window = 1048576
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 1.25
|
|
output_cost_per_m = 10.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "openrouter/mistralai/mistral-large"
|
|
display_name = "Mistral Large (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 2.0
|
|
output_cost_per_m = 6.0
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "openrouter/deepseek/deepseek-r1"
|
|
display_name = "DeepSeek R1 (OpenRouter)"
|
|
tier = "frontier"
|
|
context_window = 128000
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.55
|
|
output_cost_per_m = 2.19
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
# Free models — verified against openrouter.ai/api/v1/models on 2026-04-10.
|
|
# Previous entries (stepfun/step-3.5-flash:free, gemma-2-9b-it:free,
|
|
# llama-3.1-8b-instruct:free, qwen-2.5-7b-instruct:free, mistral-7b-instruct:free,
|
|
# zephyr-7b-beta:free, deepseek-r1:free) have all been delisted by OpenRouter
|
|
# and replaced below. See librefang#2283.
|
|
|
|
[[models]]
|
|
id = "openrouter/meta-llama/llama-3.3-70b-instruct:free"
|
|
display_name = "Llama 3.3 70B Free (OpenRouter)"
|
|
tier = "balanced"
|
|
context_window = 65536
|
|
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 = "openrouter/qwen/qwen3-next-80b-a3b-instruct:free"
|
|
display_name = "Qwen3 Next 80B Free (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 262144
|
|
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
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "openrouter/openai/gpt-oss-120b:free"
|
|
display_name = "GPT-OSS 120B Free (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
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 = "openrouter/z-ai/glm-4.5-air:free"
|
|
display_name = "GLM 4.5 Air Free (OpenRouter)"
|
|
tier = "balanced"
|
|
context_window = 131072
|
|
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 = "openrouter/google/gemma-3-27b-it:free"
|
|
display_name = "Gemma 3 27B Free (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "openrouter/nvidia/nemotron-nano-9b-v2:free"
|
|
display_name = "Nemotron Nano 9B Free (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
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 = "openrouter/ai21/jamba-large-1.7"
|
|
display_name = "AI21: Jamba Large 1.7 (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 256000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 2.0
|
|
output_cost_per_m = 8.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/alibaba/tongyi-deepresearch-30b-a3b"
|
|
display_name = "Tongyi DeepResearch 30B A3B (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.09
|
|
output_cost_per_m = 0.45
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/allenai/olmo-3.1-32b-instruct"
|
|
display_name = "AllenAI: Olmo 3.1 32B Instruct (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 65536
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.2
|
|
output_cost_per_m = 0.6
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/amazon/nova-2-lite-v1"
|
|
display_name = "Amazon: Nova 2 Lite (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 1000000
|
|
max_output_tokens = 65535
|
|
input_cost_per_m = 0.3
|
|
output_cost_per_m = 2.5
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/amazon/nova-micro-v1"
|
|
display_name = "Amazon: Nova Micro 1.0 (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 5120
|
|
input_cost_per_m = 0.035
|
|
output_cost_per_m = 0.14
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/amazon/nova-premier-v1"
|
|
display_name = "Amazon: Nova Premier 1.0 (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 1000000
|
|
max_output_tokens = 32000
|
|
input_cost_per_m = 2.5
|
|
output_cost_per_m = 12.5
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/amazon/nova-pro-v1"
|
|
display_name = "Amazon: Nova Pro 1.0 (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 300000
|
|
max_output_tokens = 5120
|
|
input_cost_per_m = 0.8
|
|
output_cost_per_m = 3.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/bytedance/ui-tars-1.5-7b"
|
|
display_name = "ByteDance: UI-TARS 7B (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 2048
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/deepcogito/cogito-v2.1-671b"
|
|
display_name = "Deep Cogito: Cogito v2.1 671B (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 1.25
|
|
output_cost_per_m = 1.25
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/essentialai/rnj-1-instruct"
|
|
display_name = "EssentialAI: Rnj 1 Instruct (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 32768
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.15
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/inclusionai/ling-2.6-1t:free"
|
|
display_name = "inclusionAI: Ling-2.6-1T (free) (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 262144
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/inclusionai/ling-2.6-flash:free"
|
|
display_name = "inclusionAI: Ling-2.6-flash (free) (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 262144
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/inflection/inflection-3-pi"
|
|
display_name = "Inflection: Inflection 3 Pi (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 8000
|
|
max_output_tokens = 1024
|
|
input_cost_per_m = 2.5
|
|
output_cost_per_m = 10.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/inflection/inflection-3-productivity"
|
|
display_name = "Inflection: Inflection 3 Productivity (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 8000
|
|
max_output_tokens = 1024
|
|
input_cost_per_m = 2.5
|
|
output_cost_per_m = 10.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/liquid/lfm-2.5-1.2b-instruct:free"
|
|
display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free) (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 32768
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/liquid/lfm-2.5-1.2b-thinking:free"
|
|
display_name = "LiquidAI: LFM2.5-1.2B-Thinking (free) (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 32768
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/nex-agi/deepseek-v3.1-nex-n1"
|
|
display_name = "Nex AGI: DeepSeek V3.1 Nex N1 (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 163840
|
|
input_cost_per_m = 0.135
|
|
output_cost_per_m = 0.5
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/nousresearch/hermes-4-405b"
|
|
display_name = "Nous: Hermes 4 405B (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 1.0
|
|
output_cost_per_m = 3.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/nousresearch/hermes-4-70b"
|
|
display_name = "Nous: Hermes 4 70B (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.13
|
|
output_cost_per_m = 0.4
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/prime-intellect/intellect-3"
|
|
display_name = "Prime Intellect: INTELLECT-3 (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.2
|
|
output_cost_per_m = 1.1
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/rekaai/reka-flash-3"
|
|
display_name = "Reka Flash 3 (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 65536
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/relace/relace-apply-3"
|
|
display_name = "Relace: Relace Apply 3 (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 256000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 0.85
|
|
output_cost_per_m = 1.25
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/relace/relace-search"
|
|
display_name = "Relace: Relace Search (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 256000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 1.0
|
|
output_cost_per_m = 3.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/switchpoint/router"
|
|
display_name = "Switchpoint Router (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.85
|
|
output_cost_per_m = 3.4
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/tngtech/deepseek-r1t2-chimera"
|
|
display_name = "TNG: DeepSeek R1T2 Chimera (OpenRouter)"
|
|
tier = "fast"
|
|
context_window = 163840
|
|
max_output_tokens = 163840
|
|
input_cost_per_m = 0.3
|
|
output_cost_per_m = 1.1
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "openrouter/writer/palmyra-x5"
|
|
display_name = "Writer: Palmyra X5 (OpenRouter)"
|
|
tier = "smart"
|
|
context_window = 1040000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.6
|
|
output_cost_per_m = 6.0
|
|
supports_streaming = true
|