mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-14 23:21:35 +00:00
Merge pull request #40901 from BerriAI/litellm_remove_fireworks_price_snapshot_tests
test(fireworks): stop pinning prices in the cost-map tests
This commit is contained in:
commit
0f03fc2985
1 changed files with 3 additions and 48 deletions
|
|
@ -4248,9 +4248,6 @@ def test_deepseek_flash_completion_cost():
|
|||
_FIREWORKS_MODELS = [
|
||||
(
|
||||
"accounts/fireworks/models/glm-5p2",
|
||||
1.4e-06,
|
||||
4.4e-06,
|
||||
1.4e-07,
|
||||
1048576,
|
||||
131072,
|
||||
False,
|
||||
|
|
@ -4258,9 +4255,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/glm-5p1",
|
||||
1.4e-06,
|
||||
4.4e-06,
|
||||
2.6e-07,
|
||||
202800,
|
||||
131072,
|
||||
False,
|
||||
|
|
@ -4268,9 +4262,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/routers/glm-5p1-fast",
|
||||
2.8e-06,
|
||||
8.8e-06,
|
||||
5.2e-07,
|
||||
202800,
|
||||
131072,
|
||||
False,
|
||||
|
|
@ -4278,9 +4269,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/qwen3p7-plus",
|
||||
4e-07,
|
||||
1.6e-06,
|
||||
8e-08,
|
||||
262144,
|
||||
65536,
|
||||
True,
|
||||
|
|
@ -4288,9 +4276,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/minimax-m3",
|
||||
3e-07,
|
||||
1.2e-06,
|
||||
6e-08,
|
||||
512000,
|
||||
512000,
|
||||
True,
|
||||
|
|
@ -4298,9 +4283,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/minimax-m2p7",
|
||||
3e-07,
|
||||
1.2e-06,
|
||||
6e-08,
|
||||
196608,
|
||||
196608,
|
||||
False,
|
||||
|
|
@ -4308,9 +4290,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/kimi-k2p7-code",
|
||||
9.5e-07,
|
||||
4e-06,
|
||||
1.9e-07,
|
||||
262144,
|
||||
32768,
|
||||
True,
|
||||
|
|
@ -4318,9 +4297,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/routers/kimi-k2p7-code-fast",
|
||||
1.9e-06,
|
||||
8e-06,
|
||||
3.8e-07,
|
||||
262144,
|
||||
32768,
|
||||
True,
|
||||
|
|
@ -4328,9 +4304,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/kimi-k2p6",
|
||||
9.5e-07,
|
||||
4e-06,
|
||||
1.6e-07,
|
||||
262144,
|
||||
32768,
|
||||
True,
|
||||
|
|
@ -4338,9 +4311,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/routers/kimi-k2p6-fast",
|
||||
2e-06,
|
||||
8e-06,
|
||||
3e-07,
|
||||
262144,
|
||||
32768,
|
||||
True,
|
||||
|
|
@ -4348,9 +4318,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/gpt-oss-120b",
|
||||
1.5e-07,
|
||||
6e-07,
|
||||
1.5e-08,
|
||||
131072,
|
||||
32768,
|
||||
False,
|
||||
|
|
@ -4358,9 +4325,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/gpt-oss-20b",
|
||||
7e-08,
|
||||
3e-07,
|
||||
3.5e-08,
|
||||
131072,
|
||||
32768,
|
||||
False,
|
||||
|
|
@ -4368,9 +4332,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/deepseek-v4-pro",
|
||||
1.74e-06,
|
||||
3.48e-06,
|
||||
1.45e-07,
|
||||
1048576,
|
||||
384000,
|
||||
False,
|
||||
|
|
@ -4378,9 +4339,6 @@ _FIREWORKS_MODELS = [
|
|||
),
|
||||
(
|
||||
"accounts/fireworks/models/deepseek-v4-flash",
|
||||
1.4e-07,
|
||||
2.8e-07,
|
||||
2.8e-08,
|
||||
1048576,
|
||||
384000,
|
||||
False,
|
||||
|
|
@ -4412,9 +4370,6 @@ _FIREWORKS_ROUTER_SHORT_FORMS = [
|
|||
def _assert_fireworks_entry(
|
||||
model_cost,
|
||||
model_path,
|
||||
expected_input,
|
||||
expected_output,
|
||||
expected_cache,
|
||||
expected_max_input,
|
||||
expected_max_output,
|
||||
expected_vision,
|
||||
|
|
@ -4424,9 +4379,9 @@ def _assert_fireworks_entry(
|
|||
assert info is not None, f"fireworks_ai/{model_path} missing from model cost map"
|
||||
assert info["litellm_provider"] == "fireworks_ai"
|
||||
assert info["mode"] == "chat"
|
||||
assert info["input_cost_per_token"] == expected_input
|
||||
assert info["output_cost_per_token"] == expected_output
|
||||
assert info["cache_read_input_token_cost"] == expected_cache
|
||||
assert info["input_cost_per_token"] > 0
|
||||
assert info["output_cost_per_token"] > 0
|
||||
assert "cache_read_input_token_cost" in info
|
||||
assert info["max_input_tokens"] == expected_max_input
|
||||
assert info["max_output_tokens"] == expected_max_output
|
||||
assert info["max_tokens"] == expected_max_output
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue