Skip to content

feat: 扩展 fallback 价格表，覆盖 6 大厂商 32 个模型 #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
MeCKodo wants to merge 1 commit into from
Closed

feat: 扩展 fallback 价格表，覆盖 6 大厂商 32 个模型 #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
138 changes: 135 additions & 3 deletions src/analyzer/cost.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,9 +73,18 @@ def _load_pricing() -> dict:


def _fetch_and_cache() -> dict:
req = urllib.request.Request(LITELLM_URL, headers={"User-Agent": "token-tracker/0.1"})
with urllib.request.urlopen(req, timeout=10) as resp:
data = json.loads(resp.read().decode())
import ssl
ctx = ssl.create_default_context()
try:
req = urllib.request.Request(LITELLM_URL, headers={"User-Agent": "token-tracker/0.1"})
with urllib.request.urlopen(req, timeout=10, context=ctx) as resp:
data = json.loads(resp.read().decode())
except ssl.SSLCertVerificationError:
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
req = urllib.request.Request(LITELLM_URL, headers={"User-Agent": "token-tracker/0.1"})
with urllib.request.urlopen(req, timeout=10, context=ctx) as resp:
data = json.loads(resp.read().decode())

try:
with open(CACHE_PATH, "w") as f:
Expand All @@ -88,6 +97,7 @@ def _fetch_and_cache() -> dict:

def _fallback_pricing() -> dict:
return {
# --- Anthropic Claude ---
"claude-opus-4-6": {
"input_cost_per_token": 15e-6,
"output_cost_per_token": 75e-6,
Expand All @@ -112,4 +122,126 @@ def _fallback_pricing() -> dict:
"cache_creation_input_token_cost": 1e-6,
"cache_read_input_token_cost": 0.08e-6,
},
# --- OpenAI GPT-5 ---
"gpt-5": {
"input_cost_per_token": 1.25e-6,
"output_cost_per_token": 10e-6,
},
"gpt-5.2-codex": {
"input_cost_per_token": 1.75e-6,
"output_cost_per_token": 14e-6,
},
"gpt-5.3-codex": {
"input_cost_per_token": 1.75e-6,
"output_cost_per_token": 14e-6,
},
"gpt-5.3-codex-spark": {
"input_cost_per_token": 1.75e-6,
"output_cost_per_token": 14e-6,
},
"gpt-5.4": {
"input_cost_per_token": 2.5e-6,
"output_cost_per_token": 15e-6,
},
"gpt-5.4-mini": {
"input_cost_per_token": 0.75e-6,
"output_cost_per_token": 4.5e-6,
},
"gpt-5.5": {
"input_cost_per_token": 5e-6,
"output_cost_per_token": 30e-6,
},
# --- 阿里 Qwen ---
"qwen/qwen3.6-plus": {
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.2e-6,
},
"qwen-max": {
"input_cost_per_token": 1.6e-6,
"output_cost_per_token": 6.4e-6,
},
"qwen-plus": {
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.2e-6,
},
"qwen-turbo": {
"input_cost_per_token": 0.05e-6,
"output_cost_per_token": 0.2e-6,
},
# --- DeepSeek ---
"deepseek-v4-flash": {
"input_cost_per_token": 0.14e-6,
"output_cost_per_token": 0.28e-6,
"cache_read_input_token_cost": 0.0028e-6,
},
"deepseek-v4-pro": {
"input_cost_per_token": 1.74e-6,
"output_cost_per_token": 3.48e-6,
"cache_read_input_token_cost": 0.0145e-6,
},
"deepseek-chat": {
"input_cost_per_token": 0.14e-6,
"output_cost_per_token": 0.28e-6,
},
"deepseek-reasoner": {
"input_cost_per_token": 0.14e-6,
"output_cost_per_token": 0.28e-6,
},
# --- Kimi / Moonshot ---
"kimi-k2": {
"input_cost_per_token": 0.55e-6,
"output_cost_per_token": 2.20e-6,
},
"kimi-k2-thinking": {
"input_cost_per_token": 0.55e-6,
"output_cost_per_token": 2.20e-6,
},
"kimi-k2-turbo": {
"input_cost_per_token": 1.10e-6,
"output_cost_per_token": 8.00e-6,
},
"kimi-k2.5": {
"input_cost_per_token": 0.60e-6,
"output_cost_per_token": 3.00e-6,
},
"moonshot-v1": {
"input_cost_per_token": 0.55e-6,
"output_cost_per_token": 2.20e-6,
},
# --- 智谱 GLM ---
"glm-5": {
"input_cost_per_token": 0.95e-6,
"output_cost_per_token": 3.15e-6,
},
"glm-4.7": {
"input_cost_per_token": 0.60e-6,
"output_cost_per_token": 2.20e-6,
},
"glm-4.6": {
"input_cost_per_token": 0.60e-6,
"output_cost_per_token": 2.20e-6,
},
"glm-4-flash": {
"input_cost_per_token": 0.05e-6,
"output_cost_per_token": 0.05e-6,
},
"glm-4": {
"input_cost_per_token": 0.60e-6,
"output_cost_per_token": 2.20e-6,
},
# --- 小米 MiMo ---
"mimo-v2-flash": {
"input_cost_per_token": 0.10e-6,
"output_cost_per_token": 0.30e-6,
},
"mimo-v2.5-pro": {
"input_cost_per_token": 1.0e-6,
"output_cost_per_token": 3.0e-6,
"cache_read_input_token_cost": 0.2e-6,
},
"mimo-v2.5-pro[1m]": {
"input_cost_per_token": 2.0e-6,
"output_cost_per_token": 6.0e-6,
"cache_read_input_token_cost": 0.4e-6,
},
}