feat(apimodels): add apimodels.app chat model prices to the cost map

Adds 36 apimodels/<model> chat rows to model_prices_and_context_window.json and the backup copy, so spend tracking prices apimodels calls instead of logging them at zero

Rates are the per token prices apimodels.app bills, as listed on https://apimodels.app/pricing and on each model page linked in the row's source field. Context limits and the function calling, vision, reasoning and prompt caching flags are copied from the model vendor's own row

The rows carry the same long prompt and off-peak rules the gateway bills with. The gpt-6 and gpt-5.6 rows rebill the whole request at 2x input and cache read and 1.5x output above 272k prompt tokens, claude-haiku-5-5 bills every rate at 5x above 100k, qwen3.7-plus bills 3x above 262,144 tokens through tiered_pricing, and the two DeepSeek Flash rows bill half rate outside 01:00-04:00 and 06:00-10:00 UTC on weekdays

Two cost tests check that an apimodels row bills cached tokens at its cache read rate and that a prompt over 272k tokens moves the whole request to the long context rates
This commit is contained in:
stimQQ 2026-10-19 18:41:09 +09:00
parent 34457b1eef
commit d52ee8f859
3 changed files with 1329 additions and 0 deletions

View file

@ -71337,6 +71337,646 @@
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-fable-5-1": {
"cache_creation_input_token_cost": 5.778e-06,
"cache_read_input_token_cost": 2.2e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"source": "https://apimodels.app/models/claude-fable-5-1",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-fable-5": {
"cache_creation_input_token_cost": 8.824e-06,
"cache_read_input_token_cost": 8.82e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"source": "https://apimodels.app/models/claude-fable-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-5-5": {
"cache_creation_input_token_cost": 3e-06,
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 2.4e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"source": "https://apimodels.app/models/claude-opus-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-5": {
"cache_creation_input_token_cost": 4.891e-06,
"cache_read_input_token_cost": 3.91e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"source": "https://apimodels.app/models/claude-opus-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-8": {
"cache_creation_input_token_cost": 1.765e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.3e-05,
"source": "https://apimodels.app/models/claude-opus-4-8",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-7": {
"cache_creation_input_token_cost": 4.595e-06,
"cache_read_input_token_cost": 3.676e-07,
"input_cost_per_token": 3.676e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.8382e-05,
"source": "https://apimodels.app/models/claude-opus-4-7",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-6": {
"cache_creation_input_token_cost": 2.206e-06,
"cache_read_input_token_cost": 1.765e-07,
"input_cost_per_token": 1.765e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8.824e-06,
"source": "https://apimodels.app/models/claude-opus-4-6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-5-20251101": {
"cache_creation_input_token_cost": 2.206e-06,
"cache_read_input_token_cost": 1.765e-07,
"input_cost_per_token": 1.765e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 200000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 8.824e-06,
"source": "https://apimodels.app/models/claude-opus-4-5-20251101",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-sonnet-5-5": {
"cache_creation_input_token_cost": 1.5e-06,
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 1.2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://apimodels.app/models/claude-sonnet-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-sonnet-5": {
"cache_creation_input_token_cost": 1.4e-06,
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 1.6e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8e-06,
"source": "https://apimodels.app/models/claude-sonnet-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-sonnet-4-6": {
"cache_creation_input_token_cost": 1.324e-06,
"cache_read_input_token_cost": 1.059e-07,
"input_cost_per_token": 1.059e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.295e-06,
"source": "https://apimodels.app/models/claude-sonnet-4-6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-haiku-5-5": {
"cache_creation_input_token_cost": 1.125e-07,
"cache_creation_input_token_cost_above_100k_tokens": 5.625e-07,
"cache_read_input_token_cost": 9e-09,
"cache_read_input_token_cost_above_100k_tokens": 4.5e-08,
"input_cost_per_token": 9e-08,
"input_cost_per_token_above_100k_tokens": 4.5e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.5e-07,
"output_cost_per_token_above_100k_tokens": 2.25e-06,
"source": "https://apimodels.app/models/claude-haiku-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-haiku-4-5-20251001": {
"cache_creation_input_token_cost": 4.41e-07,
"cache_read_input_token_cost": 3.53e-08,
"input_cost_per_token": 3.53e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 200000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.765e-06,
"source": "https://apimodels.app/models/claude-haiku-4-5-20251001",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.8-flash": {
"cache_read_input_token_cost": 1.72e-07,
"input_cost_per_token": 4.5e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.25e-06,
"source": "https://apimodels.app/models/gemini-3.8-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.6-flash": {
"cache_read_input_token_cost": 6.62e-08,
"input_cost_per_token": 6.62e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3.302e-06,
"source": "https://apimodels.app/models/gemini-3.6-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.5-flash": {
"cache_read_input_token_cost": 6.62e-08,
"input_cost_per_token": 6.62e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3.971e-06,
"source": "https://apimodels.app/models/gemini-3.5-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 3.75e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.25e-06,
"source": "https://apimodels.app/models/gemini-3.1-flash-lite",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6-astra": {
"cache_read_input_token_cost": 2.4e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.8e-07,
"input_cost_per_token": 2.4e-06,
"input_cost_per_token_above_272k_tokens": 4.8e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"source": "https://apimodels.app/models/gpt-6-astra",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6.1-sol": {
"cache_read_input_token_cost": 5e-08,
"cache_read_input_token_cost_above_272k_tokens": 1e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"output_cost_per_token_above_272k_tokens": 7.5e-06,
"source": "https://apimodels.app/models/gpt-6.1-sol",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6-sol": {
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"output_cost_per_token_above_272k_tokens": 7.5e-06,
"source": "https://apimodels.app/models/gpt-6-sol",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6-luna": {
"cache_read_input_token_cost": 9e-09,
"cache_read_input_token_cost_above_272k_tokens": 1.8e-08,
"input_cost_per_token": 9e-08,
"input_cost_per_token_above_272k_tokens": 1.8e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.5e-07,
"output_cost_per_token_above_272k_tokens": 6.75e-07,
"source": "https://apimodels.app/models/gpt-6-luna",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5.6-sol": {
"cache_read_input_token_cost": 1.32e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.64e-07,
"input_cost_per_token": 1.324e-06,
"input_cost_per_token_above_272k_tokens": 2.648e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.618e-06,
"output_cost_per_token_above_272k_tokens": 9.927e-06,
"source": "https://apimodels.app/models/gpt-5-6-sol",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5.6-terra": {
"cache_read_input_token_cost": 5.5e-08,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-07,
"input_cost_per_token": 5.51e-07,
"input_cost_per_token_above_272k_tokens": 1.102e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.309e-06,
"output_cost_per_token_above_272k_tokens": 4.9635e-06,
"source": "https://apimodels.app/models/gpt-5-6-terra",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5.6-luna": {
"cache_read_input_token_cost": 1.8e-08,
"cache_read_input_token_cost_above_272k_tokens": 3.6e-08,
"input_cost_per_token": 1.8e-07,
"input_cost_per_token_above_272k_tokens": 3.6e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 9.6e-07,
"output_cost_per_token_above_272k_tokens": 1.44e-06,
"source": "https://apimodels.app/models/gpt-5-6-luna",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5-5": {
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.8e-05,
"source": "https://apimodels.app/models/gpt-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5-4": {
"cache_read_input_token_cost": 2.5e-07,
"input_cost_per_token": 1.8e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.08e-05,
"source": "https://apimodels.app/models/gpt-5-4",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/grok-4.6": {
"cache_read_input_token_cost": 3.75e-07,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 500000,
"max_output_tokens": 500000,
"max_tokens": 500000,
"mode": "chat",
"output_cost_per_token": 4.5e-06,
"source": "https://apimodels.app/models/grok-4.6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/grok-4.5": {
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 1.275e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 500000,
"max_output_tokens": 500000,
"max_tokens": 500000,
"mode": "chat",
"output_cost_per_token": 4.25e-06,
"source": "https://apimodels.app/models/grok-4.5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/glm-5.3": {
"cache_read_input_token_cost": 2.47e-07,
"input_cost_per_token": 1.33e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.18e-06,
"source": "https://apimodels.app/models/glm-5.3",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/glm-5.2": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.26e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"source": "https://apimodels.app/models/glm-5.2",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/deepseek-v4.1-flash": {
"cache_read_input_token_cost": 5.4e-09,
"input_cost_per_token": 2.7e-07,
"litellm_provider": "apimodels",
"mode": "chat",
"off_peak_pricing": {
"cache_read_input_token_cost": 2.7e-09,
"input_cost_per_token": 1.35e-07,
"output_cost_per_token": 5.4e-07,
"windows": [
{
"hours_utc": [
"00:00-01:00",
"04:00-06:00",
"10:00-00:00"
],
"weekdays": [
1,
2,
3,
4,
5
]
},
{
"hours_utc": "00:00-00:00",
"weekdays": [
6,
7
]
}
]
},
"output_cost_per_token": 1.08e-06,
"source": "https://apimodels.app/models/deepseek-v4.1-flash"
},
"apimodels/deepseek-v4-flash": {
"cache_read_input_token_cost": 5.4e-09,
"input_cost_per_token": 2.7e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"off_peak_pricing": {
"cache_read_input_token_cost": 2.7e-09,
"input_cost_per_token": 1.35e-07,
"output_cost_per_token": 5.4e-07,
"windows": [
{
"hours_utc": [
"00:00-01:00",
"04:00-06:00",
"10:00-00:00"
],
"weekdays": [
1,
2,
3,
4,
5
]
},
{
"hours_utc": "00:00-00:00",
"weekdays": [
6,
7
]
}
]
},
"output_cost_per_token": 1.08e-06,
"source": "https://apimodels.app/models/deepseek-v4-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.8-max": {
"cache_read_input_token_cost": 2.5e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://apimodels.app/models/qwen3.8-max",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.8-flash": {
"cache_read_input_token_cost": 1.6e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.7e-07,
"source": "https://apimodels.app/models/qwen3.8-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.7-max": {
"cache_read_input_token_cost": 4.5e-07,
"input_cost_per_token": 2.25e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 6.75e-06,
"source": "https://apimodels.app/models/qwen3.7-max",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.7-plus": {
"cache_read_input_token_cost": 7.2e-08,
"input_cost_per_token": 3.6e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1.44e-06,
"source": "https://apimodels.app/models/qwen3.7-plus",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"tiered_pricing": [
{
"cache_read_input_token_cost": 7.2e-08,
"input_cost_per_token": 3.6e-07,
"output_cost_per_token": 1.44e-06,
"range": [
0,
262144
]
},
{
"cache_read_input_token_cost": 2.16e-07,
"input_cost_per_token": 1.08e-06,
"output_cost_per_token": 4.32e-06,
"range": [
262144,
1000000
]
}
]
},
"bespoke/nimble-latest": {
"input_cost_per_token": 0.0,
"litellm_provider": "bespoke",

View file

@ -71337,6 +71337,646 @@
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-fable-5-1": {
"cache_creation_input_token_cost": 5.778e-06,
"cache_read_input_token_cost": 2.2e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"source": "https://apimodels.app/models/claude-fable-5-1",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-fable-5": {
"cache_creation_input_token_cost": 8.824e-06,
"cache_read_input_token_cost": 8.82e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"source": "https://apimodels.app/models/claude-fable-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-5-5": {
"cache_creation_input_token_cost": 3e-06,
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 2.4e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"source": "https://apimodels.app/models/claude-opus-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-5": {
"cache_creation_input_token_cost": 4.891e-06,
"cache_read_input_token_cost": 3.91e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"source": "https://apimodels.app/models/claude-opus-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-8": {
"cache_creation_input_token_cost": 1.765e-06,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.3e-05,
"source": "https://apimodels.app/models/claude-opus-4-8",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-7": {
"cache_creation_input_token_cost": 4.595e-06,
"cache_read_input_token_cost": 3.676e-07,
"input_cost_per_token": 3.676e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.8382e-05,
"source": "https://apimodels.app/models/claude-opus-4-7",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-6": {
"cache_creation_input_token_cost": 2.206e-06,
"cache_read_input_token_cost": 1.765e-07,
"input_cost_per_token": 1.765e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8.824e-06,
"source": "https://apimodels.app/models/claude-opus-4-6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-opus-4-5-20251101": {
"cache_creation_input_token_cost": 2.206e-06,
"cache_read_input_token_cost": 1.765e-07,
"input_cost_per_token": 1.765e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 200000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 8.824e-06,
"source": "https://apimodels.app/models/claude-opus-4-5-20251101",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-sonnet-5-5": {
"cache_creation_input_token_cost": 1.5e-06,
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 1.2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://apimodels.app/models/claude-sonnet-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-sonnet-5": {
"cache_creation_input_token_cost": 1.4e-06,
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 1.6e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 8e-06,
"source": "https://apimodels.app/models/claude-sonnet-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-sonnet-4-6": {
"cache_creation_input_token_cost": 1.324e-06,
"cache_read_input_token_cost": 1.059e-07,
"input_cost_per_token": 1.059e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.295e-06,
"source": "https://apimodels.app/models/claude-sonnet-4-6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-haiku-5-5": {
"cache_creation_input_token_cost": 1.125e-07,
"cache_creation_input_token_cost_above_100k_tokens": 5.625e-07,
"cache_read_input_token_cost": 9e-09,
"cache_read_input_token_cost_above_100k_tokens": 4.5e-08,
"input_cost_per_token": 9e-08,
"input_cost_per_token_above_100k_tokens": 4.5e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.5e-07,
"output_cost_per_token_above_100k_tokens": 2.25e-06,
"source": "https://apimodels.app/models/claude-haiku-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/claude-haiku-4-5-20251001": {
"cache_creation_input_token_cost": 4.41e-07,
"cache_read_input_token_cost": 3.53e-08,
"input_cost_per_token": 3.53e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 200000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.765e-06,
"source": "https://apimodels.app/models/claude-haiku-4-5-20251001",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.8-flash": {
"cache_read_input_token_cost": 1.72e-07,
"input_cost_per_token": 4.5e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.25e-06,
"source": "https://apimodels.app/models/gemini-3.8-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.6-flash": {
"cache_read_input_token_cost": 6.62e-08,
"input_cost_per_token": 6.62e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3.302e-06,
"source": "https://apimodels.app/models/gemini-3.6-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.5-flash": {
"cache_read_input_token_cost": 6.62e-08,
"input_cost_per_token": 6.62e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3.971e-06,
"source": "https://apimodels.app/models/gemini-3.5-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 3.75e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.25e-06,
"source": "https://apimodels.app/models/gemini-3.1-flash-lite",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6-astra": {
"cache_read_input_token_cost": 2.4e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.8e-07,
"input_cost_per_token": 2.4e-06,
"input_cost_per_token_above_272k_tokens": 4.8e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"source": "https://apimodels.app/models/gpt-6-astra",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6.1-sol": {
"cache_read_input_token_cost": 5e-08,
"cache_read_input_token_cost_above_272k_tokens": 1e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"output_cost_per_token_above_272k_tokens": 7.5e-06,
"source": "https://apimodels.app/models/gpt-6.1-sol",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6-sol": {
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"output_cost_per_token_above_272k_tokens": 7.5e-06,
"source": "https://apimodels.app/models/gpt-6-sol",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-6-luna": {
"cache_read_input_token_cost": 9e-09,
"cache_read_input_token_cost_above_272k_tokens": 1.8e-08,
"input_cost_per_token": 9e-08,
"input_cost_per_token_above_272k_tokens": 1.8e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.5e-07,
"output_cost_per_token_above_272k_tokens": 6.75e-07,
"source": "https://apimodels.app/models/gpt-6-luna",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5.6-sol": {
"cache_read_input_token_cost": 1.32e-07,
"cache_read_input_token_cost_above_272k_tokens": 2.64e-07,
"input_cost_per_token": 1.324e-06,
"input_cost_per_token_above_272k_tokens": 2.648e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.618e-06,
"output_cost_per_token_above_272k_tokens": 9.927e-06,
"source": "https://apimodels.app/models/gpt-5-6-sol",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5.6-terra": {
"cache_read_input_token_cost": 5.5e-08,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-07,
"input_cost_per_token": 5.51e-07,
"input_cost_per_token_above_272k_tokens": 1.102e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.309e-06,
"output_cost_per_token_above_272k_tokens": 4.9635e-06,
"source": "https://apimodels.app/models/gpt-5-6-terra",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5.6-luna": {
"cache_read_input_token_cost": 1.8e-08,
"cache_read_input_token_cost_above_272k_tokens": 3.6e-08,
"input_cost_per_token": 1.8e-07,
"input_cost_per_token_above_272k_tokens": 3.6e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 9.6e-07,
"output_cost_per_token_above_272k_tokens": 1.44e-06,
"source": "https://apimodels.app/models/gpt-5-6-luna",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5-5": {
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.8e-05,
"source": "https://apimodels.app/models/gpt-5-5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/gpt-5-4": {
"cache_read_input_token_cost": 2.5e-07,
"input_cost_per_token": 1.8e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.08e-05,
"source": "https://apimodels.app/models/gpt-5-4",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/grok-4.6": {
"cache_read_input_token_cost": 3.75e-07,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 500000,
"max_output_tokens": 500000,
"max_tokens": 500000,
"mode": "chat",
"output_cost_per_token": 4.5e-06,
"source": "https://apimodels.app/models/grok-4.6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/grok-4.5": {
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 1.275e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 500000,
"max_output_tokens": 500000,
"max_tokens": 500000,
"mode": "chat",
"output_cost_per_token": 4.25e-06,
"source": "https://apimodels.app/models/grok-4.5",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true
},
"apimodels/glm-5.3": {
"cache_read_input_token_cost": 2.47e-07,
"input_cost_per_token": 1.33e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.18e-06,
"source": "https://apimodels.app/models/glm-5.3",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/glm-5.2": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.26e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"source": "https://apimodels.app/models/glm-5.2",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/deepseek-v4.1-flash": {
"cache_read_input_token_cost": 5.4e-09,
"input_cost_per_token": 2.7e-07,
"litellm_provider": "apimodels",
"mode": "chat",
"off_peak_pricing": {
"cache_read_input_token_cost": 2.7e-09,
"input_cost_per_token": 1.35e-07,
"output_cost_per_token": 5.4e-07,
"windows": [
{
"hours_utc": [
"00:00-01:00",
"04:00-06:00",
"10:00-00:00"
],
"weekdays": [
1,
2,
3,
4,
5
]
},
{
"hours_utc": "00:00-00:00",
"weekdays": [
6,
7
]
}
]
},
"output_cost_per_token": 1.08e-06,
"source": "https://apimodels.app/models/deepseek-v4.1-flash"
},
"apimodels/deepseek-v4-flash": {
"cache_read_input_token_cost": 5.4e-09,
"input_cost_per_token": 2.7e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"off_peak_pricing": {
"cache_read_input_token_cost": 2.7e-09,
"input_cost_per_token": 1.35e-07,
"output_cost_per_token": 5.4e-07,
"windows": [
{
"hours_utc": [
"00:00-01:00",
"04:00-06:00",
"10:00-00:00"
],
"weekdays": [
1,
2,
3,
4,
5
]
},
{
"hours_utc": "00:00-00:00",
"weekdays": [
6,
7
]
}
]
},
"output_cost_per_token": 1.08e-06,
"source": "https://apimodels.app/models/deepseek-v4-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.8-max": {
"cache_read_input_token_cost": 2.5e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://apimodels.app/models/qwen3.8-max",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.8-flash": {
"cache_read_input_token_cost": 1.6e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4.7e-07,
"source": "https://apimodels.app/models/qwen3.8-flash",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.7-max": {
"cache_read_input_token_cost": 4.5e-07,
"input_cost_per_token": 2.25e-06,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 6.75e-06,
"source": "https://apimodels.app/models/qwen3.7-max",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true
},
"apimodels/qwen3.7-plus": {
"cache_read_input_token_cost": 7.2e-08,
"input_cost_per_token": 3.6e-07,
"litellm_provider": "apimodels",
"max_input_tokens": 991808,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1.44e-06,
"source": "https://apimodels.app/models/qwen3.7-plus",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"tiered_pricing": [
{
"cache_read_input_token_cost": 7.2e-08,
"input_cost_per_token": 3.6e-07,
"output_cost_per_token": 1.44e-06,
"range": [
0,
262144
]
},
{
"cache_read_input_token_cost": 2.16e-07,
"input_cost_per_token": 1.08e-06,
"output_cost_per_token": 4.32e-06,
"range": [
262144,
1000000
]
}
]
},
"bespoke/nimble-latest": {
"input_cost_per_token": 0.0,
"litellm_provider": "bespoke",

View file

@ -224,3 +224,52 @@ async def test_apimodels_anthropic_messages_request_is_bridged_to_chat_completio
assert body["messages"] == [{"role": "user", "content": "Say hello"}]
assert body["max_tokens"] == 32
assert response["content"][0]["text"] == "Hello from APIMODELS"
def _completion_with_usage(model: str, usage: dict[str, object]) -> litellm.ModelResponse:
body: Final = {**_chat_completion(model), "usage": usage}
with respx.mock() as upstream:
upstream.post("https://api.apimodels.app/v1/chat/completions").respond(200, json=body)
return litellm.completion(
model=f"apimodels/{model}",
messages=[{"role": "user", "content": "Say hello"}],
api_key="apimodels-test-key",
)
def test_apimodels_chat_completion_cost_bills_cached_tokens_at_cache_read_rate():
row: Final = litellm.model_cost["apimodels/gpt-6-sol"]
response: Final = _completion_with_usage(
"gpt-6-sol",
{
"prompt_tokens": 1000,
"completion_tokens": 20,
"total_tokens": 1020,
"prompt_tokens_details": {"cached_tokens": 800},
},
)
assert row["cache_read_input_token_cost"] < row["input_cost_per_token"]
assert litellm.completion_cost(completion_response=response, model="apimodels/gpt-6-sol") == pytest.approx(
200 * row["input_cost_per_token"] + 800 * row["cache_read_input_token_cost"] + 20 * row["output_cost_per_token"]
)
def test_apimodels_prompt_over_272k_bills_the_whole_request_at_the_long_context_rates():
row: Final = litellm.model_cost["apimodels/gpt-6-sol"]
response: Final = _completion_with_usage(
"gpt-6-sol",
{
"prompt_tokens": 300_000,
"completion_tokens": 20,
"total_tokens": 300_020,
"prompt_tokens_details": {"cached_tokens": 100_000},
},
)
assert row["input_cost_per_token_above_272k_tokens"] > row["input_cost_per_token"]
assert litellm.completion_cost(completion_response=response, model="apimodels/gpt-6-sol") == pytest.approx(
200_000 * row["input_cost_per_token_above_272k_tokens"]
+ 100_000 * row["cache_read_input_token_cost_above_272k_tokens"]
+ 20 * row["output_cost_per_token_above_272k_tokens"]
)