chore: prune deprecated models across providers (#75)

* 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Remove old-generation models that are strictly superseded by current versions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Apply the same 'strictly superseded by same-provider/family successor'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.

providers/deepinfra.toml

@@ -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"