# SSoT model catalog. Pricing verified 2026-04-28 against official provider
# pages. Per RULE 0.4: source_url + verified_at on every "verified" row.
# Conversion: $1.00/Mtok = 100_000_000 micro-cents/Mtok.
#
# Schema: see _primitives/_rust/kei-model/src/model.rs
# Loader: see _primitives/_rust/kei-model/src/registry.rs

# ============================================================
# Anthropic — verified 2026-04-28
# Source: claude.com/pricing + benchlm.ai April 2026 confirmation
# ============================================================

[[models]]
id = "claude-opus-4-7"
provider = "anthropic"
display_name = "Claude Opus 4.7"
context_tokens = 200000
capabilities = ["code", "vision", "streaming", "function-call", "long-context-200k", "system-prompt"]
status = "active"
role_tags = ["expensive-code", "complex-reasoning", "code-implementer", "edit-shared", "kei-architect"]
fallback = "claude-sonnet-4-6"
notes = "Anthropic flagship 2026-04. NOTE: new tokenizer can produce 35% more tokens for same input vs prior versions."

[models.pricing]
input_per_mtok_micro = 500000000
output_per_mtok_micro = 2500000000
status = "verified"
source_url = "https://claude.com/pricing"
verified_at = "2026-04-28"

[[models]]
id = "claude-sonnet-4-6"
provider = "anthropic"
display_name = "Claude Sonnet 4.6"
context_tokens = 200000
capabilities = ["code", "vision", "streaming", "function-call", "long-context-200k", "system-prompt"]
status = "active"
role_tags = ["mid", "edit-local", "kei-researcher"]
fallback = "claude-haiku-4-5"
notes = "Anthropic mid-tier"

[models.pricing]
input_per_mtok_micro = 300000000
output_per_mtok_micro = 1500000000
status = "verified"
source_url = "https://claude.com/pricing"
verified_at = "2026-04-28"

[[models]]
id = "claude-haiku-4-5"
provider = "anthropic"
display_name = "Claude Haiku 4.5"
context_tokens = 200000
capabilities = ["code", "streaming", "function-call", "long-context-200k", "system-prompt"]
status = "active"
role_tags = ["cheap-classifier", "kei-critic", "kei-classifier"]
fallback = "gpt-4o-mini"
notes = "Anthropic cheap-tier (current kei-cortex default)"

[models.pricing]
input_per_mtok_micro = 100000000
output_per_mtok_micro = 500000000
status = "verified"
source_url = "https://claude.com/pricing"
verified_at = "2026-04-28"

# ============================================================
# OpenAI — verified 2026-04-28
# Source: openai.com/api/pricing
# ============================================================

[[models]]
id = "gpt-4o"
provider = "openai"
display_name = "GPT-4o"
context_tokens = 128000
capabilities = ["code", "vision", "streaming", "function-call", "system-prompt"]
status = "active"
role_tags = ["mid"]
fallback = "gpt-4o-mini"
notes = "OpenAI mid-tier multimodal"

[models.pricing]
input_per_mtok_micro = 250000000
output_per_mtok_micro = 1000000000
status = "verified"
source_url = "https://openai.com/api/pricing/"
verified_at = "2026-04-28"

[[models]]
id = "gpt-4o-mini"
provider = "openai"
display_name = "GPT-4o Mini"
context_tokens = 128000
capabilities = ["code", "streaming", "function-call", "system-prompt"]
status = "active"
role_tags = ["cheap"]
fallback = "deepseek-chat"
notes = "OpenAI cheap-tier (current kei-router openai default). 16x cheaper than GPT-4o."

[models.pricing]
input_per_mtok_micro = 15000000
output_per_mtok_micro = 60000000
status = "verified"
source_url = "https://openai.com/api/pricing/"
verified_at = "2026-04-28"

[[models]]
id = "o1"
provider = "openai"
display_name = "OpenAI o1"
context_tokens = 200000
capabilities = ["code", "function-call", "long-context-200k", "system-prompt"]
status = "active"
role_tags = ["complex-reasoning"]
fallback = "gpt-4o"
notes = "OpenAI reasoning-tier. NOTE: internal 'thinking tokens' inflate actual cost beyond listed rate. o3 has replaced o1 as primary; consider migration."

[models.pricing]
input_per_mtok_micro = 1500000000
output_per_mtok_micro = 6000000000
status = "verified"
source_url = "https://openai.com/api/pricing/"
verified_at = "2026-04-28"

# ============================================================
# Kimi — verified 2026-04-28
# Source: openrouter.ai (Moonshot K2 Thinking listing)
# ============================================================

[[models]]
id = "kimi-k2-thinking"
provider = "kimi"
display_name = "Kimi K2 Thinking"
context_tokens = 256000
capabilities = ["code", "streaming", "function-call", "long-context-200k", "system-prompt"]
status = "active"
role_tags = ["complex-reasoning", "mid"]
fallback = "deepseek-chat"
notes = "Moonshot Kimi reasoning-tier (current kei-router kimi default). Trillion-param MoE, 32B active. Cached input: 75% off."

[models.pricing]
input_per_mtok_micro = 60000000
output_per_mtok_micro = 250000000
status = "verified"
source_url = "https://openrouter.ai/moonshotai/kimi-k2-thinking"
verified_at = "2026-04-28"

# ============================================================
# Mistral — verified 2026-04-28
# Source: mistral.ai/pricing
# ============================================================

[[models]]
id = "mistral-large"
provider = "mistral"
display_name = "Mistral Large 3"
context_tokens = 128000
capabilities = ["code", "streaming", "function-call", "system-prompt"]
status = "active"
role_tags = ["mid"]
fallback = "mistral-small"
notes = "Mistral flagship (Large 3 generation)"

[models.pricing]
input_per_mtok_micro = 200000000
output_per_mtok_micro = 600000000
status = "verified"
source_url = "https://mistral.ai/pricing"
verified_at = "2026-04-28"

[[models]]
id = "mistral-small"
provider = "mistral"
display_name = "Mistral Small 3"
context_tokens = 128000
capabilities = ["code", "streaming", "function-call", "system-prompt"]
status = "active"
role_tags = ["cheap"]
fallback = "deepseek-chat"
notes = "Mistral cheap-tier (Small 3 generation)"

[models.pricing]
input_per_mtok_micro = 10000000
output_per_mtok_micro = 30000000
status = "verified"
source_url = "https://mistral.ai/pricing"
verified_at = "2026-04-28"

# ============================================================
# DeepSeek — verified 2026-04-28
# Source: api-docs.deepseek.com
# NOTE: deepseek-chat / deepseek-reasoner are deprecated names;
# they map to deepseek-v4-flash non-thinking / thinking modes
# respectively. Pricing here reflects v4-flash rates which apply
# to both legacy names.
# ============================================================

[[models]]
id = "deepseek-chat"
provider = "deepseek"
display_name = "DeepSeek Chat (v4-flash compat)"
context_tokens = 128000
capabilities = ["code", "streaming", "function-call", "system-prompt"]
status = "active"
role_tags = ["cheap"]
fallback = "llama-3-70b-local"
notes = "DeepSeek conversational tier. Legacy name maps to v4-flash non-thinking mode. Migrate to deepseek-v4-flash before deprecation deadline."

[models.pricing]
input_per_mtok_micro = 14000000
output_per_mtok_micro = 28000000
status = "verified"
source_url = "https://api-docs.deepseek.com/quick_start/pricing"
verified_at = "2026-04-28"

[[models]]
id = "deepseek-reasoner"
provider = "deepseek"
display_name = "DeepSeek Reasoner (v4-flash thinking compat)"
context_tokens = 128000
capabilities = ["code", "streaming", "function-call", "system-prompt"]
status = "active"
role_tags = ["complex-reasoning", "mid"]
fallback = "deepseek-chat"
notes = "DeepSeek reasoning tier. Legacy name maps to v4-flash thinking mode (75% discount applied per docs). Effective rates after discount."

[models.pricing]
input_per_mtok_micro = 43500000
output_per_mtok_micro = 87000000
status = "verified"
source_url = "https://api-docs.deepseek.com/quick_start/pricing"
verified_at = "2026-04-28"

# ============================================================
# Local (Ollama / llama.cpp / MLX) — free, marked verified-zero
# ============================================================

[[models]]
id = "llama-3-70b-local"
provider = "local"
display_name = "Llama 3 70B (local inference)"
context_tokens = 8192
capabilities = ["code", "streaming", "system-prompt"]
status = "active"
role_tags = ["free", "cheap"]
fallback = ""
notes = "Local inference (Ollama / llama.cpp / MLX). Zero per-token cost; energy + hardware-amortization tracked separately."

[models.pricing]
input_per_mtok_micro = 0
output_per_mtok_micro = 0
status = "verified"
source_url = "https://ollama.com/library/llama3"
verified_at = "2026-04-28"