provider: refresh builtin model catalog

This commit is contained in:
2026-05-31 08:17:37 +09:00
parent 164941f373
commit f6fbba4c48
4 changed files with 132 additions and 35 deletions
+36 -27
View File
@@ -1,59 +1,68 @@
# Anthropic direct
[[model]]
id = "claude-opus-4-8"
provider = "anthropic"
context_window = 1000000
capability = { tool_calling = "parallel", structured_output = "json_schema", vision = true, prompt_caching = { kind = "explicit", max_breakpoints = 4 } }
[[model]]
id = "claude-sonnet-4-6"
provider = "anthropic"
context_window = 200000
context_window = 1000000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "explicit", max_breakpoints = 4 } }
[[model]]
id = "claude-sonnet-4-5"
provider = "anthropic"
context_window = 200000
[[model]]
id = "claude-opus-4-1"
id = "claude-haiku-4-5"
provider = "anthropic"
context_window = 200000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "explicit", max_breakpoints = 4 } }
# Ollama local (capability is router-ish / ollama handles its own models)
[[model]]
id = "llama3.1"
id = "llama3.3"
provider = "ollama-local"
context_window = 128000
[[model]]
id = "qwen2.5-coder"
id = "qwen3-coder"
provider = "ollama-local"
context_window = 128000
context_window = 256000
# Codex OAuth (ChatGPT backend via Responses API)
[[model]]
id = "gpt-5.5"
provider = "codex-oauth"
context_window = 1050000
max_context_window = 272000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "gpt-5.4"
provider = "codex-oauth"
context_window = 1050000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "gpt-5-codex"
provider = "codex-oauth"
context_window = 400000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "gpt-5"
provider = "codex-oauth"
context_window = 400000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "gpt-5.5"
provider = "codex-oauth"
context_window = 1000000
max_context_window = 272000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }
# OpenRouter
[[model]]
id = "anthropic/claude-sonnet-4"
id = "anthropic/claude-opus-4.8"
provider = "openrouter"
context_window = 200000
context_window = 1000000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "openai/gpt-5"
id = "anthropic/claude-sonnet-4.6"
provider = "openrouter"
context_window = 400000
context_window = 1000000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "auto" } }
[[model]]
id = "openai/gpt-5.5"
provider = "openrouter"
context_window = 1050000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "effort", vision = true, prompt_caching = { kind = "auto" } }