scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

feat(xai): add grok-4.20 beta 2 models with pricing

Browse source 
Add three grok-4.20 beta 2 model variants from xAI:
- grok-4.20-multi-agent-beta-0309 (reasoning + multi-agent)
- grok-4.20-beta-0309-reasoning (reasoning)
- grok-4.20-beta-0309-non-reasoning

Pricing (from https://docs.x.ai/docs/models):
- Input: $2.00/1M tokens ($0.20/1M cached)
- Output: $6.00/1M tokens
- Context: 2M tokens

All variants support vision, function calling, tool choice, and web search.
Closes LIT-2171
This commit is contained in:
Ishaan Jaffer 2026-03-17 14:34:06 -07:00
parent ef9cc33ee3
commit b072bf7436
3 changed files with 144 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
litellm/model_prices_and_context_window_backup.json
View file

@ -32354,6 +32354,53 @@
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4.20-multi-agent-beta-0309": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4.20-beta-0309-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4.20-beta-0309-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-beta": {
"input_cost_per_token": 5e-06,
"litellm_provider": "xai",

47
model_prices_and_context_window.json
View file

@ -32354,6 +32354,53 @@
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4.20-multi-agent-beta-0309": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4.20-beta-0309-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-4.20-beta-0309-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"xai/grok-beta": {
"input_cost_per_token": 5e-06,
"litellm_provider": "xai",

52
tests/test_litellm/llms/xai/test_xai_cost_calculator.py
View file

@ -386,8 +386,56 @@ class TestXAICostCalculator:
completion_tokens=50,
total_tokens=150,
)
web_search_cost = cost_per_web_search_request(usage=usage, model_info={})
# Expected cost: No web search data = $0.0
assert web_search_cost == 0.0
def test_grok_4_20_beta_reasoning_cost_calculation(self):
"""Test cost calculation for grok-4.20-beta-0309-reasoning model."""
usage = Usage(prompt_tokens=100, completion_tokens=200, total_tokens=300)
prompt_cost, completion_cost = cost_per_token(
model="grok-4.20-beta-0309-reasoning", usage=usage
)
# Input: 100 tokens * $2e-6 = $0.0002
# Output: 200 tokens * $6e-6 = $0.0012
expected_prompt_cost = 100 * 2e-6
expected_completion_cost = 200 * 6e-6
assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
def test_grok_4_20_beta_non_reasoning_cost_calculation(self):
"""Test cost calculation for grok-4.20-beta-0309-non-reasoning model."""
usage = Usage(prompt_tokens=50, completion_tokens=100, total_tokens=150)
prompt_cost, completion_cost = cost_per_token(
model="grok-4.20-beta-0309-non-reasoning", usage=usage
)
# Input: 50 tokens * $2e-6 = $0.0001
# Output: 100 tokens * $6e-6 = $0.0006
expected_prompt_cost = 50 * 2e-6
expected_completion_cost = 100 * 6e-6
assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)
def test_grok_4_20_multi_agent_cost_calculation(self):
"""Test cost calculation for grok-4.20-multi-agent-beta-0309 model."""
usage = Usage(prompt_tokens=200, completion_tokens=300, total_tokens=500)
prompt_cost, completion_cost = cost_per_token(
model="grok-4.20-multi-agent-beta-0309", usage=usage
)
# Input: 200 tokens * $2e-6 = $0.0004
# Output: 300 tokens * $6e-6 = $0.0018
expected_prompt_cost = 200 * 2e-6
expected_completion_cost = 300 * 6e-6
assert math.isclose(prompt_cost, expected_prompt_cost, rel_tol=1e-10)
assert math.isclose(completion_cost, expected_completion_cost, rel_tol=1e-10)