2026-04-23 07:39:52 -05:00
|
|
|
from __future__ import annotations
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
from dataclasses import FrozenInstanceError
|
|
|
|
|
from datetime import date, timedelta
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
import pytest
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
import headroom.pricing as pricing
|
|
|
|
|
from headroom.pricing.anthropic_prices import ANTHROPIC_PRICES, get_anthropic_registry
|
|
|
|
|
from headroom.pricing.openai_prices import OPENAI_PRICES, get_openai_registry
|
|
|
|
|
from headroom.pricing.registry import ModelPricing, PricingRegistry
|
2026-04-24 15:33:30 +02:00
|
|
|
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
def test_pricing_public_exports_and_provider_registries() -> None:
|
|
|
|
|
assert pricing.ModelPricing is ModelPricing
|
|
|
|
|
assert pricing.PricingRegistry is PricingRegistry
|
|
|
|
|
assert "get_openai_registry" in pricing.__all__
|
|
|
|
|
assert "get_anthropic_registry" in pricing.__all__
|
|
|
|
|
assert "estimate_cost" in pricing.__all__
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
openai_registry = get_openai_registry()
|
|
|
|
|
anthropic_registry = get_anthropic_registry()
|
|
|
|
|
assert openai_registry.source_url == "https://openai.com/api/pricing/"
|
|
|
|
|
assert anthropic_registry.source_url == "https://www.anthropic.com/pricing"
|
|
|
|
|
assert openai_registry.prices["gpt-4o"] == OPENAI_PRICES["gpt-4o"]
|
|
|
|
|
assert (
|
|
|
|
|
anthropic_registry.prices["claude-3-5-sonnet-20241022"]
|
|
|
|
|
== ANTHROPIC_PRICES["claude-3-5-sonnet-20241022"]
|
|
|
|
|
)
|
2026-04-24 15:33:30 +02:00
|
|
|
|
feat(pricing): add DeepSeek V4 model pricing (deepseek-v4-flash, deepseek-v4-pro) (#1168)
## Description
Adds pricing support for DeepSeek V4 models (`deepseek-v4-flash` and
`deepseek-v4-pro`) when routing Headroom through `--anthropic-api-url
https://api.deepseek.com/anthropic`. The vendored LiteLLM pricing
database predates DeepSeek V4, so cost estimation silently returned
`None` for these models.
## Type of Change
- [x] New feature (non-breaking change that adds functionality)
## Changes Made
- **`headroom/pricing/deepseek_prices.py`** — New pricing data module
with `ModelPricing` dataclass entries for both V4 models, following the
pattern of `anthropic_prices.py`
- **`headroom/pricing/__init__.py`** — Exports `DEEPSEEK_PRICES`,
`get_deepseek_registry()`, `DEEPSEEK_LAST_UPDATED`
- **`headroom/pricing/litellm_pricing.py`** — Runtime injection of
DeepSeek V4 pricing into `litellm.model_cost`, plus `deepseek-` prefix
added to `resolve_litellm_model()` provider prefix list
- **`headroom/providers/anthropic.py`** — DeepSeek fallback in
`_get_pricing()` when model starts with `deepseek-` and LiteLLM is
unavailable
- **`crates/headroom-proxy/data/model_prices_and_context_window.json`**
— Vendored JSON entries (bare + provider-prefixed) for Rust-side context
window lookups
- **`tests/test_providers/test_deepseek.py`** — 20 tests across 3 test
classes (pricing data, LiteLLM injection, Anthropic fallback)
- **`tests/test_pricing.py`** — Added DeepSeek export validation
alongside existing OpenAI/Anthropic assertions
## Testing
- [x] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [ ] Manual testing performed
### Test Output
```
========================= 137 passed, 8 warnings in 8.47s =========================
```
## Real Behavior Proof
- Environment: Windows 10, Python 3.12, litellm 1.60+
- Exact command / steps: `python -c "from headroom.proxy.cost import
CostTracker; t = CostTracker();
print(t.estimate_cost('deepseek-v4-flash', input_tokens=1000000,
output_tokens=1000000))"`
- Observed result: `$0.4200` (0.14 input + 0.28 output per 1M tokens)
- Not tested: Live DeepSeek API routing via `--anthropic-api-url`
(requires API key and Docker deployment)
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable
## Additional Notes
The 90% cache discount heuristic in `AnthropicProvider.estimate_cost()`
(line 680) is a pre-existing pattern. DeepSeek V4 has much deeper cache
discounts (98-99%), but the LiteLLM path currently falls through to the
manual fallback which uses correct cached prices. A future improvement
could prefer `cache_read_input_token_cost` from model info over the
hardcoded `* 0.1` heuristic.
---------
Co-authored-by: Claude <noreply@anthropic.com>
2026-06-24 16:44:27 +02:00
|
|
|
assert "get_deepseek_registry" in pricing.__all__
|
|
|
|
|
assert "DEEPSEEK_PRICES" in pricing.__all__
|
|
|
|
|
deepseek_registry = pricing.get_deepseek_registry()
|
|
|
|
|
assert deepseek_registry.source_url == "https://api-docs.deepseek.com/quick_start/pricing"
|
|
|
|
|
flash = deepseek_registry.get_price("deepseek-v4-flash")
|
|
|
|
|
assert flash is not None
|
|
|
|
|
assert flash.input_per_1m == 0.14
|
|
|
|
|
assert flash.output_per_1m == 0.28
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
openai_registry.prices.pop("gpt-4o")
|
|
|
|
|
anthropic_registry.prices.pop("claude-3-5-sonnet-20241022")
|
|
|
|
|
assert "gpt-4o" in OPENAI_PRICES
|
|
|
|
|
assert "claude-3-5-sonnet-20241022" in ANTHROPIC_PRICES
|
2026-04-24 15:33:30 +02:00
|
|
|
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
def test_model_pricing_is_frozen() -> None:
|
|
|
|
|
model = ModelPricing(model="demo", provider="test", input_per_1m=1.5, output_per_1m=2.5)
|
|
|
|
|
with pytest.raises(FrozenInstanceError):
|
|
|
|
|
model.model = "other" # type: ignore[misc]
|
2026-04-24 15:33:30 +02:00
|
|
|
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
def test_registry_staleness_and_warning() -> None:
|
|
|
|
|
fresh = PricingRegistry(last_updated=date.today() - timedelta(days=30))
|
|
|
|
|
assert fresh.is_stale() is False
|
|
|
|
|
assert fresh.staleness_warning() is None
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
stale = PricingRegistry(
|
|
|
|
|
last_updated=date.today() - timedelta(days=31),
|
|
|
|
|
source_url="https://example.test/pricing",
|
|
|
|
|
)
|
|
|
|
|
assert stale.is_stale() is True
|
|
|
|
|
assert stale.staleness_warning() == (
|
|
|
|
|
f"Pricing data is 31 days old (last updated: {stale.last_updated})."
|
|
|
|
|
" Please verify at: https://example.test/pricing"
|
|
|
|
|
)
|
2026-04-24 15:33:30 +02:00
|
|
|
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
def test_registry_estimate_cost_with_all_token_types() -> None:
|
|
|
|
|
registry = PricingRegistry(
|
|
|
|
|
last_updated=date.today() - timedelta(days=31),
|
|
|
|
|
prices={
|
|
|
|
|
"demo": ModelPricing(
|
|
|
|
|
model="demo",
|
|
|
|
|
provider="test",
|
|
|
|
|
input_per_1m=2.0,
|
|
|
|
|
output_per_1m=4.0,
|
|
|
|
|
cached_input_per_1m=1.0,
|
|
|
|
|
batch_input_per_1m=0.5,
|
|
|
|
|
batch_output_per_1m=0.25,
|
|
|
|
|
)
|
|
|
|
|
},
|
|
|
|
|
)
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
estimate = registry.estimate_cost(
|
|
|
|
|
"demo",
|
|
|
|
|
input_tokens=1_000_000,
|
|
|
|
|
output_tokens=500_000,
|
|
|
|
|
cached_input_tokens=250_000,
|
|
|
|
|
batch_input_tokens=200_000,
|
|
|
|
|
batch_output_tokens=100_000,
|
|
|
|
|
)
|
2026-04-24 15:33:30 +02:00
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
assert estimate.cost_usd == pytest.approx(4.375)
|
|
|
|
|
assert estimate.breakdown == {
|
|
|
|
|
"input": {"tokens": 1_000_000, "rate_per_1m": 2.0, "cost_usd": 2.0},
|
|
|
|
|
"output": {"tokens": 500_000, "rate_per_1m": 4.0, "cost_usd": 2.0},
|
|
|
|
|
"cached_input": {"tokens": 250_000, "rate_per_1m": 1.0, "cost_usd": 0.25},
|
|
|
|
|
"batch_input": {"tokens": 200_000, "rate_per_1m": 0.5, "cost_usd": 0.1},
|
|
|
|
|
"batch_output": {"tokens": 100_000, "rate_per_1m": 0.25, "cost_usd": 0.025},
|
|
|
|
|
}
|
|
|
|
|
assert estimate.pricing_date == registry.last_updated
|
|
|
|
|
assert estimate.is_stale is True
|
|
|
|
|
assert estimate.warning == (
|
|
|
|
|
f"Pricing data is 31 days old (last updated: {registry.last_updated})."
|
|
|
|
|
)
|
2026-04-24 15:33:30 +02:00
|
|
|
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
def test_registry_estimate_cost_zero_usage_returns_empty_breakdown() -> None:
|
|
|
|
|
registry = PricingRegistry(
|
|
|
|
|
last_updated=date.today(),
|
|
|
|
|
prices={
|
|
|
|
|
"demo": ModelPricing(model="demo", provider="test", input_per_1m=1.0, output_per_1m=2.0)
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
estimate = registry.estimate_cost("demo")
|
|
|
|
|
assert estimate.cost_usd == 0.0
|
|
|
|
|
assert estimate.breakdown == {}
|
|
|
|
|
assert estimate.is_stale is False
|
|
|
|
|
assert estimate.warning is None
|
2026-04-24 15:33:30 +02:00
|
|
|
|
|
|
|
|
|
2026-04-23 07:39:52 -05:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
|
("kwargs", "message"),
|
|
|
|
|
[
|
|
|
|
|
({}, "Model 'missing' not found in registry"),
|
|
|
|
|
({"cached_input_tokens": 1}, "Model 'demo' does not have cached input pricing"),
|
|
|
|
|
({"batch_input_tokens": 1}, "Model 'demo' does not have batch input pricing"),
|
|
|
|
|
({"batch_output_tokens": 1}, "Model 'demo' does not have batch output pricing"),
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
def test_registry_estimate_cost_error_paths(kwargs: dict[str, int], message: str) -> None:
|
|
|
|
|
registry = PricingRegistry(
|
|
|
|
|
last_updated=date.today(),
|
|
|
|
|
prices={
|
|
|
|
|
"demo": ModelPricing(model="demo", provider="test", input_per_1m=1.0, output_per_1m=2.0)
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
with pytest.raises(ValueError, match=message):
|
|
|
|
|
registry.estimate_cost("missing" if not kwargs else "demo", **kwargs)
|