# 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 = 1000000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "explicit", max_breakpoints = 4 } }

[[model]]
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 = "llama3.3"
provider = "ollama-local"
context_window = 128000

[[model]]
id = "qwen3-coder"
provider = "ollama-local"
context_window = 256000

# Codex OAuth (ChatGPT backend via Responses API)
[[model]]
id = "gpt-5.5"
provider = "codex-oauth"
# OpenAI docs advertise GPT-5.5 with a 1.05M context window, but Codex OAuth /
# ChatGPT backend access is effectively limited around 272k tokens; this
# provider-specific entry records that effective route limit directly.
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" } }

# OpenRouter
[[model]]
id = "anthropic/claude-opus-4.8"
provider = "openrouter"
context_window = 1000000
capability = { tool_calling = "parallel", structured_output = "json_schema", reasoning = "budget_tokens", vision = true, prompt_caching = { kind = "auto" } }

[[model]]
id = "anthropic/claude-sonnet-4.6"
provider = "openrouter"
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" } }