metergraph-core 0.8.3__tar.gz → 0.8.5__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {metergraph_core-0.8.3/src/metergraph_core.egg-info → metergraph_core-0.8.5}/PKG-INFO +31 -1
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/README.md +30 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/pyproject.toml +1 -1
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/__init__.py +6 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/billing.py +5 -1
- metergraph_core-0.8.5/src/metergraph_core/calls.py +184 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/data/models.yaml +32 -1
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/data/prices.yaml +1801 -79
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/extractors.py +7 -2
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/models.py +5 -1
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/retrieval.py +2 -1
- {metergraph_core-0.8.3 → metergraph_core-0.8.5/src/metergraph_core.egg-info}/PKG-INFO +31 -1
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core.egg-info/SOURCES.txt +1 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/MANIFEST.in +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/setup.cfg +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/catalog.py +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/catalog_delta.py +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/data/sources.yaml +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/loader.py +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/refresh.py +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/responses.py +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core/sources.py +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core.egg-info/dependency_links.txt +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core.egg-info/requires.txt +0 -0
- {metergraph_core-0.8.3 → metergraph_core-0.8.5}/src/metergraph_core.egg-info/top_level.txt +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: metergraph-core
|
|
3
|
-
Version: 0.8.
|
|
3
|
+
Version: 0.8.5
|
|
4
4
|
Summary: Open, effective-dated LLM pricing catalog and deterministic cost calculator for popular models across major providers and gateways, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, OpenRouter, Vercel AI Gateway, and more.
|
|
5
5
|
Author: Metergraph
|
|
6
6
|
License-Expression: Apache-2.0
|
|
@@ -603,3 +603,33 @@ lifecycles.
|
|
|
603
603
|
The model registry version is an ISO date. When more than one registry ships on
|
|
604
604
|
the same date, append a positive revision such as `2026-09-25.2` so consumers
|
|
605
605
|
can distinguish the policies while pricing validation still uses that date.
|
|
606
|
+
|
|
607
|
+
|
|
608
|
+
## Complete call pricing
|
|
609
|
+
|
|
610
|
+
`price_call_from_response` combines token costs with supported retrieval fees.
|
|
611
|
+
`cost_from_response` remains token-only. Retrieval pricing supports Anthropic
|
|
612
|
+
`web_search` and `web_fetch` on `anthropic-api`; other observed scopes are unresolved.
|
|
613
|
+
|
|
614
|
+
```python
|
|
615
|
+
from metergraph_core import price_call_from_response
|
|
616
|
+
|
|
617
|
+
result = price_call_from_response(
|
|
618
|
+
"anthropic",
|
|
619
|
+
{"type": "message", "model": "claude-sonnet-5-5", "usage": {
|
|
620
|
+
"input_tokens": 1000, "output_tokens": 100,
|
|
621
|
+
"server_tool_use": {"web_search_requests": 2},
|
|
622
|
+
}},
|
|
623
|
+
at="2026-10-20T00:00:00Z",
|
|
624
|
+
)
|
|
625
|
+
assert str(result.cost_usd) == "0.02300000"
|
|
626
|
+
```
|
|
627
|
+
|
|
628
|
+
`cost_usd` is set only when the call is fully priced. `known_subtotal_usd`
|
|
629
|
+
contains exact components; `estimated_total_usd` separates token fallback
|
|
630
|
+
estimates when all retrieval fees are known. Missing charges are reported in
|
|
631
|
+
`missing_dimensions`. Counts must be nonnegative integers.
|
|
632
|
+
|
|
633
|
+
For normalized usage, use `price_call` with `ModelUsage` and `RetrievalUsage`.
|
|
634
|
+
To compose an existing token result from the same catalog, use `compose_call_cost`.
|
|
635
|
+
`resolve_billing` accepts complete-call results for gateway reconciliation.
|
|
@@ -573,3 +573,33 @@ lifecycles.
|
|
|
573
573
|
The model registry version is an ISO date. When more than one registry ships on
|
|
574
574
|
the same date, append a positive revision such as `2026-09-25.2` so consumers
|
|
575
575
|
can distinguish the policies while pricing validation still uses that date.
|
|
576
|
+
|
|
577
|
+
|
|
578
|
+
## Complete call pricing
|
|
579
|
+
|
|
580
|
+
`price_call_from_response` combines token costs with supported retrieval fees.
|
|
581
|
+
`cost_from_response` remains token-only. Retrieval pricing supports Anthropic
|
|
582
|
+
`web_search` and `web_fetch` on `anthropic-api`; other observed scopes are unresolved.
|
|
583
|
+
|
|
584
|
+
```python
|
|
585
|
+
from metergraph_core import price_call_from_response
|
|
586
|
+
|
|
587
|
+
result = price_call_from_response(
|
|
588
|
+
"anthropic",
|
|
589
|
+
{"type": "message", "model": "claude-sonnet-5-5", "usage": {
|
|
590
|
+
"input_tokens": 1000, "output_tokens": 100,
|
|
591
|
+
"server_tool_use": {"web_search_requests": 2},
|
|
592
|
+
}},
|
|
593
|
+
at="2026-10-20T00:00:00Z",
|
|
594
|
+
)
|
|
595
|
+
assert str(result.cost_usd) == "0.02300000"
|
|
596
|
+
```
|
|
597
|
+
|
|
598
|
+
`cost_usd` is set only when the call is fully priced. `known_subtotal_usd`
|
|
599
|
+
contains exact components; `estimated_total_usd` separates token fallback
|
|
600
|
+
estimates when all retrieval fees are known. Missing charges are reported in
|
|
601
|
+
`missing_dimensions`. Counts must be nonnegative integers.
|
|
602
|
+
|
|
603
|
+
For normalized usage, use `price_call` with `ModelUsage` and `RetrievalUsage`.
|
|
604
|
+
To compose an existing token result from the same catalog, use `compose_call_cost`.
|
|
605
|
+
`resolve_billing` accepts complete-call results for gateway reconciliation.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "metergraph-core"
|
|
3
|
-
version = "0.8.
|
|
3
|
+
version = "0.8.5"
|
|
4
4
|
description = "Open, effective-dated LLM pricing catalog and deterministic cost calculator for popular models across major providers and gateways, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, OpenRouter, Vercel AI Gateway, and more."
|
|
5
5
|
readme = "README.md"
|
|
6
6
|
license = "Apache-2.0"
|
|
@@ -155,3 +155,9 @@ __all__ = [
|
|
|
155
155
|
"search_operation_for_channel",
|
|
156
156
|
"validate_model_registry",
|
|
157
157
|
]
|
|
158
|
+
|
|
159
|
+
from .calls import (CallCostResult, RetrievalComponent, RetrievalUsage, compose_call_cost,
|
|
160
|
+
price_call, price_call_from_response, response_retrieval_usage)
|
|
161
|
+
|
|
162
|
+
__all__ += ["CallCostResult", "RetrievalComponent", "RetrievalUsage", "compose_call_cost",
|
|
163
|
+
"price_call", "price_call_from_response", "response_retrieval_usage"]
|
|
@@ -168,7 +168,7 @@ def _disputed(
|
|
|
168
168
|
|
|
169
169
|
|
|
170
170
|
def resolve_billing(
|
|
171
|
-
catalog_result: CostResult,
|
|
171
|
+
catalog_result: "CostResult | CallCostResult",
|
|
172
172
|
evidence: GatewayBillingEvidence,
|
|
173
173
|
*,
|
|
174
174
|
disputes: Iterable[Dispute] = (),
|
|
@@ -231,3 +231,7 @@ def resolve_billing(
|
|
|
231
231
|
catalog_price_id=catalog_result.price_id,
|
|
232
232
|
catalog_reasons=reasons,
|
|
233
233
|
)
|
|
234
|
+
|
|
235
|
+
from typing import TYPE_CHECKING
|
|
236
|
+
if TYPE_CHECKING:
|
|
237
|
+
from .calls import CallCostResult
|
|
@@ -0,0 +1,184 @@
|
|
|
1
|
+
"""Compose token and counted retrieval costs from one catalog snapshot."""
|
|
2
|
+
from __future__ import annotations
|
|
3
|
+
|
|
4
|
+
from dataclasses import dataclass
|
|
5
|
+
from decimal import Decimal
|
|
6
|
+
from typing import Any, Mapping, Sequence
|
|
7
|
+
|
|
8
|
+
from .catalog import CostResult, ModelUsage, direct_channel_for_provider, normalize_provider
|
|
9
|
+
from .loader import LoadedCatalog
|
|
10
|
+
from .responses import _as_mapping, _bundled_catalog, cost_from_response, response_format
|
|
11
|
+
|
|
12
|
+
_ZERO = Decimal('0')
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
@dataclass(frozen=True, slots=True)
|
|
16
|
+
class RetrievalUsage:
|
|
17
|
+
operation: str
|
|
18
|
+
units: Any
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
@dataclass(frozen=True, slots=True)
|
|
22
|
+
class RetrievalComponent:
|
|
23
|
+
operation: str
|
|
24
|
+
units: Any
|
|
25
|
+
cost_usd: Decimal | None
|
|
26
|
+
price_id: str | None
|
|
27
|
+
basis: str
|
|
28
|
+
reasons: tuple[str, ...] = ()
|
|
29
|
+
source_url: str | None = None
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
@dataclass(frozen=True, slots=True)
|
|
33
|
+
class CallCostResult:
|
|
34
|
+
token_cost: CostResult
|
|
35
|
+
retrieval: tuple[RetrievalComponent, ...]
|
|
36
|
+
cost_usd: Decimal | None
|
|
37
|
+
known_subtotal_usd: Decimal
|
|
38
|
+
estimated_total_usd: Decimal | None
|
|
39
|
+
status: str
|
|
40
|
+
token_basis: str
|
|
41
|
+
missing_dimensions: tuple[str, ...]
|
|
42
|
+
catalog_hash: str
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
@property
|
|
46
|
+
def publisher(self) -> str | None:
|
|
47
|
+
return self.token_cost.publisher
|
|
48
|
+
|
|
49
|
+
@property
|
|
50
|
+
def price_id(self) -> str | None:
|
|
51
|
+
return self.token_cost.price_id
|
|
52
|
+
|
|
53
|
+
@property
|
|
54
|
+
def reasons(self) -> tuple[str, ...]:
|
|
55
|
+
return tuple(dict.fromkeys((*self.token_cost.reasons,
|
|
56
|
+
*(f"missing_{d}" for d in self.missing_dimensions))))
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
def compose_call_cost(
|
|
60
|
+
token_cost: CostResult, *, catalog: LoadedCatalog,
|
|
61
|
+
retrieval: Sequence[RetrievalUsage] = (), provider: str | None = None,
|
|
62
|
+
channel: str | None = None, region: str = 'global',
|
|
63
|
+
) -> CallCostResult:
|
|
64
|
+
"""Combine retrieval with a token result from the same catalog and time.
|
|
65
|
+
|
|
66
|
+
Partial token results remain estimates, excluded from the known subtotal.
|
|
67
|
+
"""
|
|
68
|
+
if token_cost.effective_at is None:
|
|
69
|
+
raise ValueError('token_cost must carry its effective_at')
|
|
70
|
+
if token_cost.price is not None:
|
|
71
|
+
selected = catalog.lookup_price(model=token_cost.canonical_model,
|
|
72
|
+
channel=token_cost.price.pricing_channel, region=token_cost.price.region,
|
|
73
|
+
at=token_cost.effective_at)
|
|
74
|
+
if selected.price != token_cost.price:
|
|
75
|
+
raise ValueError('token price does not match the catalog snapshot')
|
|
76
|
+
if len({item.operation for item in retrieval}) != len(retrieval):
|
|
77
|
+
raise ValueError('retrieval operations must be aggregated once per call')
|
|
78
|
+
resolved_channel = token_cost.price.pricing_channel if token_cost.price else (channel or direct_channel_for_provider(provider))
|
|
79
|
+
publisher = token_cost.publisher or normalize_provider(provider or '')
|
|
80
|
+
missing = list(token_cost.missing_dimensions)
|
|
81
|
+
token_basis = ('exact' if token_cost.status == 'priced' else
|
|
82
|
+
'fallback_estimate' if token_cost.cost_usd is not None else 'unknown')
|
|
83
|
+
# Retrieval rates are USD. Do not add them to a different currency.
|
|
84
|
+
currency_ok = token_cost.currency in (None, 'USD')
|
|
85
|
+
known = token_cost.cost_usd if token_basis == 'exact' and currency_ok else _ZERO
|
|
86
|
+
if not currency_ok:
|
|
87
|
+
missing.append('currency')
|
|
88
|
+
token_basis = 'unknown'
|
|
89
|
+
parts = []
|
|
90
|
+
for usage in retrieval:
|
|
91
|
+
if resolved_channel == 'anthropic-api' and publisher == 'anthropic' and usage.operation in {'web_search', 'web_fetch'}:
|
|
92
|
+
fee = catalog.price_retrieval(channel=resolved_channel, operation=usage.operation,
|
|
93
|
+
units=usage.units, at=token_cost.effective_at, region=region)
|
|
94
|
+
part = RetrievalComponent(usage.operation, usage.units, fee.cost_usd,
|
|
95
|
+
fee.price_id, 'exact' if fee.status == 'priced' else 'unknown', fee.reasons, fee.source_url)
|
|
96
|
+
else:
|
|
97
|
+
part = RetrievalComponent(usage.operation, usage.units, None, None,
|
|
98
|
+
'unknown', ('unsupported_retrieval_scope',))
|
|
99
|
+
part = RetrievalComponent(part.operation,
|
|
100
|
+
part.units if type(part.units) is int and part.units >= 0 else None,
|
|
101
|
+
part.cost_usd, part.price_id, part.basis, part.reasons, part.source_url)
|
|
102
|
+
parts.append(part)
|
|
103
|
+
if part.cost_usd is None:
|
|
104
|
+
missing.append(f'retrieval.{usage.operation}')
|
|
105
|
+
else:
|
|
106
|
+
known += part.cost_usd
|
|
107
|
+
unresolved = any(p.basis == 'unknown' for p in parts)
|
|
108
|
+
status = ('unpriced' if token_cost.price is None or token_cost.status == 'unpriced' else
|
|
109
|
+
'partial' if token_basis != 'exact' or unresolved or missing else 'priced')
|
|
110
|
+
estimated = None
|
|
111
|
+
if token_basis == 'fallback_estimate' and not unresolved:
|
|
112
|
+
estimated = token_cost.cost_usd + sum((p.cost_usd or _ZERO for p in parts), _ZERO)
|
|
113
|
+
return CallCostResult(token_cost, tuple(parts), known if status == 'priced' else None,
|
|
114
|
+
known, estimated, status, token_basis, tuple(dict.fromkeys(missing)), catalog.content_hash)
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
def price_call(
|
|
118
|
+
*, model: Any, usage: ModelUsage, at: Any, catalog: LoadedCatalog | None = None,
|
|
119
|
+
provider: str | None = None, channel: str | None = None, region: str | None = None,
|
|
120
|
+
retrieval: Sequence[RetrievalUsage] = (),
|
|
121
|
+
) -> CallCostResult:
|
|
122
|
+
"""Price normalized token and retrieval usage against one snapshot."""
|
|
123
|
+
loaded = catalog if catalog is not None else _bundled_catalog()
|
|
124
|
+
tokens = loaded.calculate_cost(model=model, usage=usage, at=at, provider=provider,
|
|
125
|
+
channel=channel, region=region)
|
|
126
|
+
return compose_call_cost(tokens, catalog=loaded, retrieval=retrieval, provider=provider,
|
|
127
|
+
channel=channel or direct_channel_for_provider(provider), region=region or 'global')
|
|
128
|
+
|
|
129
|
+
|
|
130
|
+
def response_retrieval_usage(response: Any, *, format: str | None = None) -> tuple[RetrievalUsage, ...]:
|
|
131
|
+
"""Read operation metadata without reading prompt or response text.
|
|
132
|
+
|
|
133
|
+
Tool evidence without a valid usage counter remains unresolved.
|
|
134
|
+
"""
|
|
135
|
+
data = _as_mapping(response)
|
|
136
|
+
detected = format or response_format(data)
|
|
137
|
+
if detected == 'anthropic.messages':
|
|
138
|
+
usage = data.get('usage')
|
|
139
|
+
usage = usage if isinstance(usage, Mapping) else {}
|
|
140
|
+
server = usage.get('server_tool_use')
|
|
141
|
+
if 'server_tool_use' in usage and not isinstance(server, Mapping):
|
|
142
|
+
return (RetrievalUsage('web_search', None),)
|
|
143
|
+
server = server or {}
|
|
144
|
+
found = [RetrievalUsage(op, server[key]) for key, op in (
|
|
145
|
+
('web_search_requests', 'web_search'), ('web_fetch_requests', 'web_fetch')) if key in server]
|
|
146
|
+
observed = set()
|
|
147
|
+
content = data.get('content')
|
|
148
|
+
if isinstance(content, list):
|
|
149
|
+
for block in content:
|
|
150
|
+
if isinstance(block, Mapping) and block.get('type') == 'server_tool_use':
|
|
151
|
+
name = block.get('name')
|
|
152
|
+
if name in ('web_search', 'web_fetch'):
|
|
153
|
+
observed.add(name)
|
|
154
|
+
found.extend(RetrievalUsage(op, None) for op in sorted(observed) if op not in {f.operation for f in found})
|
|
155
|
+
return tuple(found)
|
|
156
|
+
if detected == 'gemini.generate_content':
|
|
157
|
+
candidates = data.get('candidates')
|
|
158
|
+
if isinstance(candidates, list):
|
|
159
|
+
for item in candidates:
|
|
160
|
+
metadata = item.get('groundingMetadata') if isinstance(item, Mapping) else None
|
|
161
|
+
if isinstance(metadata, Mapping) and ('webSearchQueries' in metadata or 'groundingChunks' in metadata):
|
|
162
|
+
# Grounding evidence does not establish billable query count.
|
|
163
|
+
return (RetrievalUsage('google_search_grounding', None),)
|
|
164
|
+
if detected == 'openai.responses':
|
|
165
|
+
output = data.get('output')
|
|
166
|
+
if isinstance(output, list):
|
|
167
|
+
count = sum(1 for item in output if isinstance(item, Mapping) and item.get('type') == 'web_search_call')
|
|
168
|
+
if count:
|
|
169
|
+
return (RetrievalUsage('web_search', count),)
|
|
170
|
+
return ()
|
|
171
|
+
|
|
172
|
+
|
|
173
|
+
def price_call_from_response(
|
|
174
|
+
provider: str, response: Any, *, catalog: LoadedCatalog | None = None,
|
|
175
|
+
model: str | None = None, at: Any = None, channel: str | None = None,
|
|
176
|
+
region: str | None = None, service_tier: str | None = None, format: str | None = None,
|
|
177
|
+
) -> CallCostResult:
|
|
178
|
+
"""Price a provider response, including supported counted retrieval fees."""
|
|
179
|
+
loaded = catalog if catalog is not None else _bundled_catalog()
|
|
180
|
+
tokens = cost_from_response(provider, response, catalog=loaded, model=model, at=at,
|
|
181
|
+
channel=channel, region=region, service_tier=service_tier, format=format)
|
|
182
|
+
return compose_call_cost(tokens, catalog=loaded,
|
|
183
|
+
retrieval=response_retrieval_usage(response, format=format), provider=provider,
|
|
184
|
+
channel=channel or direct_channel_for_provider(provider), region=region or 'global')
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
version: '2026-10-
|
|
1
|
+
version: '2026-10-29'
|
|
2
2
|
models:
|
|
3
3
|
- canonical_id: openai/gpt-5.6-sol
|
|
4
4
|
display_name: GPT-5.6 Sol
|
|
@@ -888,6 +888,30 @@ models:
|
|
|
888
888
|
execution_profiles:
|
|
889
889
|
- default
|
|
890
890
|
display_name: Kimi K3.1 Pro Highspeed (direct)
|
|
891
|
+
- canonical_id: minimax/minimax-m3.1-flash
|
|
892
|
+
display_name: MiniMax M3.1 Flash
|
|
893
|
+
publisher: minimax
|
|
894
|
+
released: '2026-10-19' # https://www.minimax.io/blog/minimax-m31f
|
|
895
|
+
routes:
|
|
896
|
+
- key: default:minimax/minimax-m3.1-flash
|
|
897
|
+
id: minimax/minimax-m3.1-flash
|
|
898
|
+
provider: vercel
|
|
899
|
+
model_id: minimax/minimax-m3.1-flash
|
|
900
|
+
pricing_channel: vercel-ai-gateway
|
|
901
|
+
execution_profiles:
|
|
902
|
+
- default
|
|
903
|
+
- canonical_id: mistral/mistral-small-4
|
|
904
|
+
display_name: Mistral Small 4
|
|
905
|
+
publisher: mistral
|
|
906
|
+
released: '2026-03-16' # https://docs.mistral.ai/models/mistral-small-4-0-26-03
|
|
907
|
+
routes:
|
|
908
|
+
- key: default:mistral:mistral-small-2603
|
|
909
|
+
id: mistral:mistral-small-2603
|
|
910
|
+
provider: mistral
|
|
911
|
+
model_id: mistral-small-2603
|
|
912
|
+
pricing_channel: mistral-api
|
|
913
|
+
execution_profiles:
|
|
914
|
+
- default
|
|
891
915
|
execution_profiles:
|
|
892
916
|
- id: default
|
|
893
917
|
routes:
|
|
@@ -963,6 +987,8 @@ execution_profiles:
|
|
|
963
987
|
- default:openai:gpt-6.1-terra
|
|
964
988
|
- default:moonshotai:kimi-k3.1-pro
|
|
965
989
|
- default:moonshotai:kimi-k3.1-pro-highspeed
|
|
990
|
+
- default:minimax/minimax-m3.1-flash
|
|
991
|
+
- default:mistral:mistral-small-2603
|
|
966
992
|
- id: bedrock
|
|
967
993
|
routes:
|
|
968
994
|
- bedrock:anthropic/claude-sonnet-5
|
|
@@ -1029,6 +1055,7 @@ offer_groups:
|
|
|
1029
1055
|
- default:deepseek/deepseek-v4.1-flash-1017
|
|
1030
1056
|
- default:deepseek/deepseek-v4.1-flash-1017-fast
|
|
1031
1057
|
- default:inception/mercury-3
|
|
1058
|
+
- default:minimax/minimax-m3.1-flash
|
|
1032
1059
|
- id: fireworks
|
|
1033
1060
|
credential: FIREWORKS_API_KEY
|
|
1034
1061
|
routes:
|
|
@@ -1059,6 +1086,10 @@ offer_groups:
|
|
|
1059
1086
|
routes:
|
|
1060
1087
|
- default:moonshotai:kimi-k3.1-pro
|
|
1061
1088
|
- default:moonshotai:kimi-k3.1-pro-highspeed
|
|
1089
|
+
- id: mistral-direct
|
|
1090
|
+
credential: MISTRAL_API_KEY
|
|
1091
|
+
routes:
|
|
1092
|
+
- default:mistral:mistral-small-2603
|
|
1062
1093
|
- id: bedrock
|
|
1063
1094
|
credential: null
|
|
1064
1095
|
routes:
|