phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update model cost map to indicate which allows system prompt and which don't

Browse source
This commit is contained in:
Krrish Dholakia 2023-09-20 16:34:02 -07:00
parent 93123d57ad
commit 64793e7ed7
1 changed files with 132 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

198
model_prices_and_context_window.json
View file

@ -3,394 +3,460 @@
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.00003, "input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006, "output_cost_per_token": 0.00006,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-4-0314": { "gpt-4-0314": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.00003, "input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006, "output_cost_per_token": 0.00006,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-4-0613": { "gpt-4-0613": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.00003, "input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006, "output_cost_per_token": 0.00006,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-4-32k": { "gpt-4-32k": {
"max_tokens": 32768, "max_tokens": 32768,
"input_cost_per_token": 0.00006, "input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012, "output_cost_per_token": 0.00012,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-4-32k-0314": { "gpt-4-32k-0314": {
"max_tokens": 32768, "max_tokens": 32768,
"input_cost_per_token": 0.00006, "input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012, "output_cost_per_token": 0.00012,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-4-32k-0613": { "gpt-4-32k-0613": {
"max_tokens": 32768, "max_tokens": 32768,
"input_cost_per_token": 0.00006, "input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012, "output_cost_per_token": 0.00012,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-3.5-turbo": { "gpt-3.5-turbo": {
"max_tokens": 4097, "max_tokens": 4097,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-3.5-turbo-0301": { "gpt-3.5-turbo-0301": {
"max_tokens": 4097, "max_tokens": 4097,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-3.5-turbo-0613": { "gpt-3.5-turbo-0613": {
"max_tokens": 4097, "max_tokens": 4097,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-3.5-turbo-16k": { "gpt-3.5-turbo-16k": {
"max_tokens": 16385, "max_tokens": 16385,
"input_cost_per_token": 0.000003, "input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004, "output_cost_per_token": 0.000004,
"litellm_provider": "openai" "litellm_provider": "openai",
"mode": "chat"
}, },
"gpt-3.5-turbo-16k-0613": { "gpt-3.5-turbo-16k-0613": {
"max_tokens": 16385, "max_tokens": 16385,
"input_cost_per_token": 0.000003, "input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004 "output_cost_per_token": 0.000004,
"mode": "chat"
}, },
"text-davinci-003": { "text-davinci-003": {
"max_tokens": 4097, "max_tokens": 4097,
"input_cost_per_token": 0.000002, "input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"text-curie-001": { "text-curie-001": {
"max_tokens": 2049, "max_tokens": 2049,
"input_cost_per_token": 0.000002, "input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"text-babbage-001": { "text-babbage-001": {
"max_tokens": 2049, "max_tokens": 2049,
"input_cost_per_token": 0.0000004, "input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000004, "output_cost_per_token": 0.0000004,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"text-ada-001": { "text-ada-001": {
"max_tokens": 2049, "max_tokens": 2049,
"input_cost_per_token": 0.0000004, "input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000004, "output_cost_per_token": 0.0000004,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"babbage-002": { "babbage-002": {
"max_tokens": 16384, "max_tokens": 16384,
"input_cost_per_token": 0.0000004, "input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000004, "output_cost_per_token": 0.0000004,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"davinci-002": { "davinci-002": {
"max_tokens": 16384, "max_tokens": 16384,
"input_cost_per_token": 0.000002, "input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"gpt-3.5-turbo-instruct": { "gpt-3.5-turbo-instruct": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "text-completion-openai" "litellm_provider": "text-completion-openai",
"mode": "completion"
}, },
"claude-instant-1": { "claude-instant-1": {
"max_tokens": 100000, "max_tokens": 100000,
"input_cost_per_token": 0.00000163, "input_cost_per_token": 0.00000163,
"output_cost_per_token": 0.00000551, "output_cost_per_token": 0.00000551,
"litellm_provider": "anthropic" "litellm_provider": "anthropic",
"mode": "chat"
}, },
"claude-instant-1.2": { "claude-instant-1.2": {
"max_tokens": 100000, "max_tokens": 100000,
"input_cost_per_token": 0.00000163, "input_cost_per_token": 0.00000163,
"output_cost_per_token": 0.00000551, "output_cost_per_token": 0.00000551,
"litellm_provider": "anthropic" "litellm_provider": "anthropic",
"mode": "chat"
}, },
"claude-2": { "claude-2": {
"max_tokens": 100000, "max_tokens": 100000,
"input_cost_per_token": 0.00001102, "input_cost_per_token": 0.00001102,
"output_cost_per_token": 0.00003268, "output_cost_per_token": 0.00003268,
"litellm_provider": "anthropic" "litellm_provider": "anthropic",
"mode": "chat"
}, },
"text-bison": { "text-bison": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-text-models" "litellm_provider": "vertex_ai-text-models",
"mode": "completion"
}, },
"text-bison@001": { "text-bison@001": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-text-models" "litellm_provider": "vertex_ai-text-models",
"mode": "completion"
}, },
"chat-bison": { "chat-bison": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-chat-models" "litellm_provider": "vertex_ai-chat-models",
"mode": "chat"
}, },
"chat-bison@001": { "chat-bison@001": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-chat-models" "litellm_provider": "vertex_ai-chat-models",
"mode": "chat"
}, },
"chat-bison-32k": { "chat-bison-32k": {
"max_tokens": 32000, "max_tokens": 32000,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-chat-models" "litellm_provider": "vertex_ai-chat-models",
"mode": "chat"
}, },
"code-bison": { "code-bison": {
"max_tokens": 6144, "max_tokens": 6144,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-code-text-models" "litellm_provider": "vertex_ai-code-text-models",
"mode": "chat"
}, },
"code-bison@001": { "code-bison@001": {
"max_tokens": 6144, "max_tokens": 6144,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-code-text-models" "litellm_provider": "vertex_ai-code-text-models",
"mode": "completion"
}, },
"code-gecko@001": { "code-gecko@001": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-chat-models" "litellm_provider": "vertex_ai-chat-models",
"mode": "completion"
}, },
"code-gecko@latest": { "code-gecko@latest": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-chat-models" "litellm_provider": "vertex_ai-chat-models",
"mode": "completion"
}, },
"codechat-bison": { "codechat-bison": {
"max_tokens": 6144, "max_tokens": 6144,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-code-chat-models" "litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat"
}, },
"codechat-bison@001": { "codechat-bison@001": {
"max_tokens": 6144, "max_tokens": 6144,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-code-chat-models" "litellm_provider": "vertex_ai-code-chat-models",
"mode": "chat"
}, },
"codechat-bison-32k": { "codechat-bison-32k": {
"max_tokens": 32000, "max_tokens": 32000,
"input_cost_per_token": 0.000000125, "input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000125, "output_cost_per_token": 0.000000125,
"litellm_provider": "vertex_ai-chat-models" "litellm_provider": "vertex_ai-chat-models",
"mode": "chat"
}, },
"command-nightly": { "command-nightly": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000015, "input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015, "output_cost_per_token": 0.000015,
"litellm_provider": "cohere" "litellm_provider": "cohere",
"mode": "completion"
}, },
"command": { "command": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000015, "input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015, "output_cost_per_token": 0.000015,
"litellm_provider": "cohere" "litellm_provider": "cohere",
"mode": "completion"
}, },
"command-light": { "command-light": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000015, "input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015, "output_cost_per_token": 0.000015,
"litellm_provider": "cohere" "litellm_provider": "cohere",
"mode": "completion"
}, },
"command-medium-beta": { "command-medium-beta": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000015, "input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015, "output_cost_per_token": 0.000015,
"litellm_provider": "cohere" "litellm_provider": "cohere",
"mode": "completion"
}, },
"command-xlarge-beta": { "command-xlarge-beta": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000015, "input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015, "output_cost_per_token": 0.000015,
"litellm_provider": "cohere" "litellm_provider": "cohere",
"mode": "completion"
}, },
"replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1": { "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1": {
"max_tokens": 4096, "max_tokens": 4096,
"litellm_provider": "replicate" "litellm_provider": "replicate",
"mode": "chat"
}, },
"openrouter/openai/gpt-3.5-turbo": { "openrouter/openai/gpt-3.5-turbo": {
"max_tokens": 4095, "max_tokens": 4095,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002, "output_cost_per_token": 0.000002,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/openai/gpt-3.5-turbo-16k": { "openrouter/openai/gpt-3.5-turbo-16k": {
"max_tokens": 16383, "max_tokens": 16383,
"input_cost_per_token": 0.000003, "input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004, "output_cost_per_token": 0.000004,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/openai/gpt-4": { "openrouter/openai/gpt-4": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.00003, "input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006, "output_cost_per_token": 0.00006,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/anthropic/claude-instant-v1": { "openrouter/anthropic/claude-instant-v1": {
"max_tokens": 100000, "max_tokens": 100000,
"input_cost_per_token": 0.00000163, "input_cost_per_token": 0.00000163,
"output_cost_per_token": 0.00000551, "output_cost_per_token": 0.00000551,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/anthropic/claude-2": { "openrouter/anthropic/claude-2": {
"max_tokens": 100000, "max_tokens": 100000,
"input_cost_per_token": 0.00001102, "input_cost_per_token": 0.00001102,
"output_cost_per_token": 0.00003268, "output_cost_per_token": 0.00003268,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/google/palm-2-chat-bison": { "openrouter/google/palm-2-chat-bison": {
"max_tokens": 8000, "max_tokens": 8000,
"input_cost_per_token": 0.0000005, "input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005, "output_cost_per_token": 0.0000005,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/google/palm-2-codechat-bison": { "openrouter/google/palm-2-codechat-bison": {
"max_tokens": 8000, "max_tokens": 8000,
"input_cost_per_token": 0.0000005, "input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005, "output_cost_per_token": 0.0000005,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/meta-llama/llama-2-13b-chat": { "openrouter/meta-llama/llama-2-13b-chat": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.0000002, "input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002, "output_cost_per_token": 0.0000002,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/meta-llama/llama-2-70b-chat": { "openrouter/meta-llama/llama-2-70b-chat": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.0000015, "input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000015,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/meta-llama/codellama-34b-instruct": { "openrouter/meta-llama/codellama-34b-instruct": {
"max_tokens": 8096, "max_tokens": 8096,
"input_cost_per_token": 0.0000005, "input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005, "output_cost_per_token": 0.0000005,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/nousresearch/nous-hermes-llama2-13b": { "openrouter/nousresearch/nous-hermes-llama2-13b": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.0000002, "input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002, "output_cost_per_token": 0.0000002,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/mancer/weaver": { "openrouter/mancer/weaver": {
"max_tokens": 8000, "max_tokens": 8000,
"input_cost_per_token": 0.000005625, "input_cost_per_token": 0.000005625,
"output_cost_per_token": 0.000005625, "output_cost_per_token": 0.000005625,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/gryphe/mythomax-l2-13b": { "openrouter/gryphe/mythomax-l2-13b": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.000001875, "input_cost_per_token": 0.000001875,
"output_cost_per_token": 0.000001875, "output_cost_per_token": 0.000001875,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/jondurbin/airoboros-l2-70b-2.1": { "openrouter/jondurbin/airoboros-l2-70b-2.1": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000013875, "input_cost_per_token": 0.000013875,
"output_cost_per_token": 0.000013875, "output_cost_per_token": 0.000013875,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/undi95/remm-slerp-l2-13b": { "openrouter/undi95/remm-slerp-l2-13b": {
"max_tokens": 6144, "max_tokens": 6144,
"input_cost_per_token": 0.000001875, "input_cost_per_token": 0.000001875,
"output_cost_per_token": 0.000001875, "output_cost_per_token": 0.000001875,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"openrouter/pygmalionai/mythalion-13b": { "openrouter/pygmalionai/mythalion-13b": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000001875, "input_cost_per_token": 0.000001875,
"output_cost_per_token": 0.000001875, "output_cost_per_token": 0.000001875,
"litellm_provider": "openrouter" "litellm_provider": "openrouter",
"mode": "chat"
}, },
"j2-ultra": { "j2-ultra": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.000015, "input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015, "output_cost_per_token": 0.000015,
"litellm_provider": "ai21" "litellm_provider": "ai21",
"mode": "completion"
}, },
"j2-mid": { "j2-mid": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.00001, "input_cost_per_token": 0.00001,
"output_cost_per_token": 0.00001, "output_cost_per_token": 0.00001,
"litellm_provider": "ai21" "litellm_provider": "ai21",
"mode": "completion"
}, },
"j2-light": { "j2-light": {
"max_tokens": 8192, "max_tokens": 8192,
"input_cost_per_token": 0.000003, "input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000003, "output_cost_per_token": 0.000003,
"litellm_provider": "ai21" "litellm_provider": "ai21",
"mode": "completion"
}, },
"dolphin": { "dolphin": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.00002, "input_cost_per_token": 0.00002,
"output_cost_per_token": 0.00002, "output_cost_per_token": 0.00002,
"litellm_provider": "nlp_cloud" "litellm_provider": "nlp_cloud",
"mode": "completion"
}, },
"chatdolphin": { "chatdolphin": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.00002, "input_cost_per_token": 0.00002,
"output_cost_per_token": 0.00002, "output_cost_per_token": 0.00002,
"litellm_provider": "nlp_cloud" "litellm_provider": "nlp_cloud",
"mode": "chat"
}, },
"luminous-base": { "luminous-base": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.00003, "input_cost_per_token": 0.00003,
"output_cost_per_token": 0.000033, "output_cost_per_token": 0.000033,
"litellm_provider": "aleph_alpha" "litellm_provider": "aleph_alpha",
"mode": "completion"
}, },
"luminous-base-control": { "luminous-base-control": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.0000375, "input_cost_per_token": 0.0000375,
"output_cost_per_token": 0.00004125, "output_cost_per_token": 0.00004125,
"litellm_provider": "aleph_alpha" "litellm_provider": "aleph_alpha",
"mode": "chat"
}, },
"luminous-extended": { "luminous-extended": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.000045, "input_cost_per_token": 0.000045,
"output_cost_per_token": 0.0000495, "output_cost_per_token": 0.0000495,
"litellm_provider": "aleph_alpha" "litellm_provider": "aleph_alpha",
"mode": "completion"
}, },
"luminous-extended-control": { "luminous-extended-control": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.00005625, "input_cost_per_token": 0.00005625,
"output_cost_per_token": 0.000061875, "output_cost_per_token": 0.000061875,
"litellm_provider": "aleph_alpha" "litellm_provider": "aleph_alpha",
"mode": "chat"
}, },
"luminous-supreme": { "luminous-supreme": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.000175, "input_cost_per_token": 0.000175,
"output_cost_per_token": 0.0001925, "output_cost_per_token": 0.0001925,
"litellm_provider": "aleph_alpha" "litellm_provider": "aleph_alpha",
"mode": "completion"
}, },
"luminous-supreme-control": { "luminous-supreme-control": {
"max_tokens": 2048, "max_tokens": 2048,
"input_cost_per_token": 0.00021875, "input_cost_per_token": 0.00021875,
"output_cost_per_token": 0.000240625, "output_cost_per_token": 0.000240625,
"litellm_provider": "aleph_alpha" "litellm_provider": "aleph_alpha",
"mode": "chat"
}, },
"together-ai-up-to-3b": { "together-ai-up-to-3b": {
"input_cost_per_token": 0.0000001, "input_cost_per_token": 0.0000001,