feat(xai): add grok-4.3 and grok-4.3-latest to model_prices_and_conte… (#27154)
* feat(xai): add grok-4.3 and grok-4.3-latest to model_prices_and_context_window.json xAI's docs page now lists grok-4.3 as the recommended chat / coding model: "We strongly recommend all API callers use grok-4.3. It is the most intelligent and fastest model we've built." (https://docs.x.ai/docs/models) Pricing/specs sourced from xAI's published model metadata: - input: $1.25 / 1M tokens (<=200k), $2.50 / 1M tokens (>200k) - output: $2.50 / 1M tokens (<=200k), $5.00 / 1M tokens (>200k) - cached: $0.20 / 1M tokens (<=200k), $0.40 / 1M tokens (>200k) - context: 1,000,000 tokens - capabilities: vision, reasoning, function calling, structured outputs, prompt caching, web search Adds two entries: `xai/grok-4.3` (canonical) and `xai/grok-4.3-latest` (alias), mirroring the pattern used for the rest of the xAI/Grok-4 family. * test(xai): add model_info test for grok-4.3 + sync backup cost map - Mirror xai/grok-4.3 and xai/grok-4.3-latest entries into litellm/model_prices_and_context_window_backup.json so the bundled model cost map matches the canonical model_prices_and_context_window.json. - Add tests/test_litellm/test_xai_grok_4_3_model_metadata.py covering pricing tiers, capability flags, context window, provider routing, and parity between the main and backup cost maps. - Point 'source' at the live xAI models page (the per-model URL https://docs.x.ai/docs/models/grok-4.3 currently 404s). Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> --------- Co-authored-by: shin-watcher <shin-watcher@berri.ai> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
This commit is contained in:
ishaan-berri
GitHub
parent
a67b7a7e87
commit
fee5900acc
@ -34940,6 +34940,48 @@
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"xai/grok-4.3": {
|
||||
"cache_read_input_token_cost": 2e-07,
|
||||
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"input_cost_per_token_above_200k_tokens": 2.5e-06,
|
||||
"litellm_provider": "xai",
|
||||
"max_input_tokens": 1000000,
|
||||
"max_output_tokens": 1000000,
|
||||
"max_tokens": 1000000,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 2.5e-06,
|
||||
"output_cost_per_token_above_200k_tokens": 5e-06,
|
||||
"source": "https://docs.x.ai/docs/models",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"xai/grok-4.3-latest": {
|
||||
"cache_read_input_token_cost": 2e-07,
|
||||
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"input_cost_per_token_above_200k_tokens": 2.5e-06,
|
||||
"litellm_provider": "xai",
|
||||
"max_input_tokens": 1000000,
|
||||
"max_output_tokens": 1000000,
|
||||
"max_tokens": 1000000,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 2.5e-06,
|
||||
"output_cost_per_token_above_200k_tokens": 5e-06,
|
||||
"source": "https://docs.x.ai/docs/models",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"xai/grok-beta": {
|
||||
"input_cost_per_token": 5e-06,
|
||||
"litellm_provider": "xai",
|
||||
|
||||
@ -34945,6 +34945,48 @@
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"xai/grok-4.3": {
|
||||
"cache_read_input_token_cost": 2e-07,
|
||||
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"input_cost_per_token_above_200k_tokens": 2.5e-06,
|
||||
"litellm_provider": "xai",
|
||||
"max_input_tokens": 1000000,
|
||||
"max_output_tokens": 1000000,
|
||||
"max_tokens": 1000000,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 2.5e-06,
|
||||
"output_cost_per_token_above_200k_tokens": 5e-06,
|
||||
"source": "https://docs.x.ai/docs/models",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"xai/grok-4.3-latest": {
|
||||
"cache_read_input_token_cost": 2e-07,
|
||||
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"input_cost_per_token_above_200k_tokens": 2.5e-06,
|
||||
"litellm_provider": "xai",
|
||||
"max_input_tokens": 1000000,
|
||||
"max_output_tokens": 1000000,
|
||||
"max_tokens": 1000000,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 2.5e-06,
|
||||
"output_cost_per_token_above_200k_tokens": 5e-06,
|
||||
"source": "https://docs.x.ai/docs/models",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"xai/grok-beta": {
|
||||
"input_cost_per_token": 5e-06,
|
||||
"litellm_provider": "xai",
|
||||
|
||||
62
tests/test_litellm/test_xai_grok_4_3_model_metadata.py
Normal file
62
tests/test_litellm/test_xai_grok_4_3_model_metadata.py
Normal file
@ -0,0 +1,62 @@
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", ["xai/grok-4.3", "xai/grok-4.3-latest"])
|
||||
def test_xai_grok_4_3_model_info(model):
|
||||
json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json"
|
||||
with open(json_path) as f:
|
||||
model_cost = json.load(f)
|
||||
|
||||
info = model_cost.get(model)
|
||||
assert (
|
||||
info is not None
|
||||
), f"{model} not found in model_prices_and_context_window.json"
|
||||
|
||||
assert info["litellm_provider"] == "xai"
|
||||
assert info["mode"] == "chat"
|
||||
|
||||
assert info["input_cost_per_token"] == 1.25e-06
|
||||
assert info["output_cost_per_token"] == 2.5e-06
|
||||
assert info["cache_read_input_token_cost"] == 2e-07
|
||||
|
||||
assert info["input_cost_per_token_above_200k_tokens"] == 2.5e-06
|
||||
assert info["output_cost_per_token_above_200k_tokens"] == 5e-06
|
||||
assert info["cache_read_input_token_cost_above_200k_tokens"] == 4e-07
|
||||
|
||||
assert info["max_input_tokens"] == 1000000
|
||||
assert info["max_output_tokens"] == 1000000
|
||||
assert info["max_tokens"] == 1000000
|
||||
|
||||
assert info["supports_function_calling"] is True
|
||||
assert info["supports_prompt_caching"] is True
|
||||
assert info["supports_reasoning"] is True
|
||||
assert info["supports_response_schema"] is True
|
||||
assert info["supports_tool_choice"] is True
|
||||
assert info["supports_vision"] is True
|
||||
assert info["supports_web_search"] is True
|
||||
|
||||
routed_model, provider, _, _ = get_llm_provider(model=model)
|
||||
assert routed_model == model.split("/", 1)[1]
|
||||
assert provider == "xai"
|
||||
|
||||
|
||||
def test_xai_grok_4_3_backup_matches_main():
|
||||
"""Ensure the bundled model cost map stays in sync with the canonical file."""
|
||||
repo_root = Path(__file__).parents[2]
|
||||
main_path = repo_root / "model_prices_and_context_window.json"
|
||||
backup_path = repo_root / "litellm" / "model_prices_and_context_window_backup.json"
|
||||
|
||||
with open(main_path) as f:
|
||||
main_cost = json.load(f)
|
||||
with open(backup_path) as f:
|
||||
backup_cost = json.load(f)
|
||||
|
||||
for model in ("xai/grok-4.3", "xai/grok-4.3-latest"):
|
||||
assert backup_cost.get(model) == main_cost.get(
|
||||
model
|
||||
), f"{model} differs between main and backup model cost maps"
|
||||
Loading…
Reference in New Issue
Block a user