@@ -8,8 +8,21 @@
"default_small_model_id": "anthropic/claude-3.5-haiku",
"models": [
{
- "id": "nvidia/nemotron-nano-9b-v2",
- "name": "NVIDIA: Nemotron Nano 9B V2",
+ "id": "meituan/longcat-flash-chat",
+ "name": "Meituan: LongCat Flash Chat",
+ "cost_per_1m_in": 0.24999987999999998,
+ "cost_per_1m_out": 0.999999888,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 131072,
+ "default_max_tokens": 13107,
+ "can_reason": false,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
+ {
+ "id": "nvidia/nemotron-nano-9b-v2:free",
+ "name": "NVIDIA: Nemotron Nano 9B V2 (free)",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
@@ -20,6 +33,19 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
+ {
+ "id": "nvidia/nemotron-nano-9b-v2",
+ "name": "NVIDIA: Nemotron Nano 9B V2",
+ "cost_per_1m_in": 0.04,
+ "cost_per_1m_out": 0.16,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 131072,
+ "default_max_tokens": 13107,
+ "can_reason": true,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
{
"id": "openrouter/sonoma-dusk-alpha",
"name": "Sonoma Dusk Alpha",
@@ -62,8 +88,8 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -101,12 +127,12 @@
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.08967387,
+ "cost_per_1m_out": 0.358695612,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 26214,
+ "default_max_tokens": 131072,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -127,21 +153,8 @@
{
"id": "nousresearch/hermes-4-70b",
"name": "Nous: Hermes 4 70B",
- "cost_per_1m_in": 0.09329544,
- "cost_per_1m_out": 0.3733632,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": true,
- "has_reasoning_efforts": false,
- "supports_attachments": false
- },
- {
- "id": "nousresearch/hermes-4-405b",
- "name": "Nous: Hermes 4 405B",
- "cost_per_1m_in": 0.1999188,
- "cost_per_1m_out": 0.800064,
+ "cost_per_1m_in": 0.127173852,
+ "cost_per_1m_out": 0.5086955952000001,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -205,12 +218,12 @@
{
"id": "z-ai/glm-4.5v",
"name": "Z.AI: GLM 4.5V",
- "cost_per_1m_in": 0.6,
+ "cost_per_1m_in": 0.5,
"cost_per_1m_out": 1.7999999999999998,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.11,
+ "cost_per_1m_out_cached": 0,
"context_window": 65536,
- "default_max_tokens": 8192,
+ "default_max_tokens": 32768,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -301,7 +314,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 16384,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -335,8 +348,8 @@
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
- "cost_per_1m_in": 0.051830799999999996,
- "cost_per_1m_out": 0.207424,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -348,8 +361,8 @@
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen: Qwen3 30B A3B Instruct 2507",
- "cost_per_1m_in": 0.051830799999999996,
- "cost_per_1m_out": 0.207424,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -361,8 +374,8 @@
{
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
- "cost_per_1m_in": 0.32986602,
- "cost_per_1m_out": 1.3201056,
+ "cost_per_1m_in": 0.41249980199999997,
+ "cost_per_1m_out": 1.6499998152000002,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -390,9 +403,9 @@
"cost_per_1m_in": 0.19999999999999998,
"cost_per_1m_out": 1.1,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131076,
- "default_max_tokens": 13107,
+ "cost_per_1m_out_cached": 0.03,
+ "context_window": 131072,
+ "default_max_tokens": 48000,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -400,8 +413,8 @@
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen: Qwen3 235B A22B Thinking 2507",
- "cost_per_1m_in": 0.077968332,
- "cost_per_1m_out": 0.31202496,
+ "cost_per_1m_in": 0.0974999532,
+ "cost_per_1m_out": 0.38999995632,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -439,8 +452,8 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.37,
- "cost_per_1m_out": 1.5,
+ "cost_per_1m_in": 0.44999999999999996,
+ "cost_per_1m_out": 1.7999999999999998,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -465,12 +478,12 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.12,
- "cost_per_1m_out": 0.59,
+ "cost_per_1m_in": 0.19999999999999998,
+ "cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 131072,
+ "default_max_tokens": 26214,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -621,10 +634,10 @@
{
"id": "x-ai/grok-3-mini",
"name": "xAI: Grok 3 Mini",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 4,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.15,
+ "cost_per_1m_out_cached": 0.075,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,
@@ -751,8 +764,8 @@
{
"id": "mistralai/devstral-small-2505",
"name": "Mistral: Devstral Small 2505",
- "cost_per_1m_in": 0.01999188,
- "cost_per_1m_out": 0.0800064,
+ "cost_per_1m_in": 0.035869548,
+ "cost_per_1m_out": 0.14347824480000002,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -891,19 +904,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "id": "qwen/qwen3-235b-a22b:free",
- "name": "Qwen: Qwen3 235B A22B (free)",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": false,
- "has_reasoning_efforts": false,
- "supports_attachments": false
- },
{
"id": "qwen/qwen3-235b-a22b",
"name": "Qwen: Qwen3 235B A22B",
@@ -998,10 +998,10 @@
{
"id": "x-ai/grok-3-mini-beta",
"name": "xAI: Grok 3 Mini Beta",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 4,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.15,
+ "cost_per_1m_out_cached": 0.075,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,
@@ -1037,12 +1037,12 @@
{
"id": "meta-llama/llama-4-maverick",
"name": "Meta: Llama 4 Maverick",
- "cost_per_1m_in": 0.18,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.22,
+ "cost_per_1m_out": 0.88,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1048576,
- "default_max_tokens": 524288,
+ "default_max_tokens": 104857,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1366,8 +1366,8 @@
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 65536,
- "default_max_tokens": 6553,
+ "context_window": 128000,
+ "default_max_tokens": 2014,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1375,12 +1375,12 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.038000000000000006,
+ "cost_per_1m_in": 0.039,
"cost_per_1m_out": 0.12,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 8192,
+ "default_max_tokens": 4096,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1490,8 +1490,8 @@
"supports_attachments": false
},
{
- "id": "anthropic/claude-3.5-haiku",
- "name": "Anthropic: Claude 3.5 Haiku",
+ "id": "anthropic/claude-3.5-haiku-20241022",
+ "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)",
"cost_per_1m_in": 0.7999999999999999,
"cost_per_1m_out": 4,
"cost_per_1m_in_cached": 1,
@@ -1503,8 +1503,8 @@
"supports_attachments": true
},
{
- "id": "anthropic/claude-3.5-haiku-20241022",
- "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)",
+ "id": "anthropic/claude-3.5-haiku",
+ "name": "Anthropic: Claude 3.5 Haiku",
"cost_per_1m_in": 0.7999999999999999,
"cost_per_1m_out": 4,
"cost_per_1m_in_cached": 1,
@@ -1645,19 +1645,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "id": "nousresearch/hermes-3-llama-3.1-70b",
- "name": "Nous: Hermes 3 70B Instruct",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 0.39999999999999997,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 12288,
- "default_max_tokens": 1228,
- "can_reason": false,
- "has_reasoning_efforts": false,
- "supports_attachments": false
- },
{
"id": "openai/gpt-4o-2024-08-06",
"name": "OpenAI: GPT-4o (2024-08-06)",
@@ -1674,8 +1661,8 @@
{
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Meta: Llama 3.1 8B Instruct",
- "cost_per_1m_in": 0.015,
- "cost_per_1m_out": 0.02,
+ "cost_per_1m_in": 0.03,
+ "cost_per_1m_out": 0.049999999999999996,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -1687,12 +1674,12 @@
{
"id": "meta-llama/llama-3.1-405b-instruct",
"name": "Meta: Llama 3.1 405B Instruct",
- "cost_per_1m_in": 3,
- "cost_per_1m_out": 3,
+ "cost_per_1m_in": 0.7999999999999999,
+ "cost_per_1m_out": 0.7999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
+ "context_window": 32768,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1700,12 +1687,12 @@
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.28,
+ "cost_per_1m_in": 0.22999999999999998,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 8192,
+ "default_max_tokens": 13107,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1724,8 +1711,8 @@
"supports_attachments": false
},
{
- "id": "openai/gpt-4o-mini",
- "name": "OpenAI: GPT-4o-mini",
+ "id": "openai/gpt-4o-mini-2024-07-18",
+ "name": "OpenAI: GPT-4o-mini (2024-07-18)",
"cost_per_1m_in": 0.15,
"cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
@@ -1737,8 +1724,8 @@
"supports_attachments": true
},
{
- "id": "openai/gpt-4o-mini-2024-07-18",
- "name": "OpenAI: GPT-4o-mini (2024-07-18)",
+ "id": "openai/gpt-4o-mini",
+ "name": "OpenAI: GPT-4o-mini",
"cost_per_1m_in": 0.15,
"cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
@@ -1763,10 +1750,10 @@
"supports_attachments": true
},
{
- "id": "mistralai/mistral-7b-instruct:free",
- "name": "Mistral: Mistral 7B Instruct (free)",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
+ "id": "mistralai/mistral-7b-instruct-v0.3",
+ "name": "Mistral: Mistral 7B Instruct v0.3",
+ "cost_per_1m_in": 0.028,
+ "cost_per_1m_out": 0.054,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
@@ -1776,10 +1763,10 @@
"supports_attachments": false
},
{
- "id": "mistralai/mistral-7b-instruct",
- "name": "Mistral: Mistral 7B Instruct",
- "cost_per_1m_in": 0.028,
- "cost_per_1m_out": 0.054,
+ "id": "mistralai/mistral-7b-instruct:free",
+ "name": "Mistral: Mistral 7B Instruct (free)",
+ "cost_per_1m_in": 0,
+ "cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
@@ -1789,8 +1776,8 @@
"supports_attachments": false
},
{
- "id": "mistralai/mistral-7b-instruct-v0.3",
- "name": "Mistral: Mistral 7B Instruct v0.3",
+ "id": "mistralai/mistral-7b-instruct",
+ "name": "Mistral: Mistral 7B Instruct",
"cost_per_1m_in": 0.028,
"cost_per_1m_out": 0.054,
"cost_per_1m_in_cached": 0,
@@ -1840,6 +1827,19 @@
"has_reasoning_efforts": false,
"supports_attachments": true
},
+ {
+ "id": "openai/gpt-4o-2024-05-13",
+ "name": "OpenAI: GPT-4o (2024-05-13)",
+ "cost_per_1m_in": 5,
+ "cost_per_1m_out": 15,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 128000,
+ "default_max_tokens": 2048,
+ "can_reason": false,
+ "has_reasoning_efforts": false,
+ "supports_attachments": true
+ },
{
"id": "openai/gpt-4o",
"name": "OpenAI: GPT-4o",
@@ -1867,17 +1867,17 @@
"supports_attachments": true
},
{
- "id": "openai/gpt-4o-2024-05-13",
- "name": "OpenAI: GPT-4o (2024-05-13)",
- "cost_per_1m_in": 5,
- "cost_per_1m_out": 15,
+ "id": "meta-llama/llama-3-70b-instruct",
+ "name": "Meta: Llama 3 70B Instruct",
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 128000,
- "default_max_tokens": 2048,
+ "context_window": 8192,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
- "supports_attachments": true
+ "supports_attachments": false
},
{
"id": "meta-llama/llama-3-8b-instruct",
@@ -1892,19 +1892,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "id": "meta-llama/llama-3-70b-instruct",
- "name": "Meta: Llama 3 70B Instruct",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 0.39999999999999997,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 8192,
- "default_max_tokens": 8192,
- "can_reason": false,
- "has_reasoning_efforts": false,
- "supports_attachments": false
- },
{
"id": "mistralai/mixtral-8x22b-instruct",
"name": "Mistral: Mixtral 8x22B Instruct",
@@ -2036,36 +2023,36 @@
"supports_attachments": false
},
{
- "id": "openai/gpt-3.5-turbo-0613",
- "name": "OpenAI: GPT-3.5 Turbo (older v0613)",
- "cost_per_1m_in": 1,
- "cost_per_1m_out": 2,
+ "id": "openai/gpt-4-turbo-preview",
+ "name": "OpenAI: GPT-4 Turbo Preview",
+ "cost_per_1m_in": 10,
+ "cost_per_1m_out": 30,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 4095,
+ "context_window": 128000,
"default_max_tokens": 2048,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
},
{
- "id": "openai/gpt-4-turbo-preview",
- "name": "OpenAI: GPT-4 Turbo Preview",
- "cost_per_1m_in": 10,
- "cost_per_1m_out": 30,
+ "id": "openai/gpt-3.5-turbo-0613",
+ "name": "OpenAI: GPT-3.5 Turbo (older v0613)",
+ "cost_per_1m_in": 1,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 128000,
+ "context_window": 4095,
"default_max_tokens": 2048,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
},
{
- "id": "mistralai/mistral-small",
- "name": "Mistral Small",
- "cost_per_1m_in": 0.19999999999999998,
- "cost_per_1m_out": 0.6,
+ "id": "mistralai/mistral-tiny",
+ "name": "Mistral Tiny",
+ "cost_per_1m_in": 0.25,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
@@ -2075,10 +2062,10 @@
"supports_attachments": false
},
{
- "id": "mistralai/mistral-tiny",
- "name": "Mistral Tiny",
- "cost_per_1m_in": 0.25,
- "cost_per_1m_out": 0.25,
+ "id": "mistralai/mistral-small",
+ "name": "Mistral Small",
+ "cost_per_1m_in": 0.19999999999999998,
+ "cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
@@ -2140,8 +2127,8 @@
"supports_attachments": false
},
{
- "id": "openai/gpt-4",
- "name": "OpenAI: GPT-4",
+ "id": "openai/gpt-4-0314",
+ "name": "OpenAI: GPT-4 (older v0314)",
"cost_per_1m_in": 30,
"cost_per_1m_out": 60,
"cost_per_1m_in_cached": 0,
@@ -2153,8 +2140,8 @@
"supports_attachments": false
},
{
- "id": "openai/gpt-4-0314",
- "name": "OpenAI: GPT-4 (older v0314)",
+ "id": "openai/gpt-4",
+ "name": "OpenAI: GPT-4",
"cost_per_1m_in": 30,
"cost_per_1m_out": 60,
"cost_per_1m_in_cached": 0,