@@ -7,6 +7,19 @@
"default_large_model_id": "anthropic/claude-sonnet-4",
"default_small_model_id": "anthropic/claude-3.5-haiku",
"models": [
+ {
+ "id": "nvidia/nemotron-nano-9b-v2",
+ "name": "NVIDIA: Nemotron Nano 9B V2",
+ "cost_per_1m_in": 0,
+ "cost_per_1m_out": 0,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 128000,
+ "default_max_tokens": 12800,
+ "can_reason": true,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
{
"id": "openrouter/sonoma-dusk-alpha",
"name": "Sonoma Dusk Alpha",
@@ -88,12 +101,12 @@
{
"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": 0.0713,
+ "cost_per_1m_out": 0.2852,
"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
@@ -111,6 +124,19 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
+ {
+ "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",
@@ -257,8 +283,8 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.5,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 0.49,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -309,8 +335,8 @@
{
"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,
@@ -361,12 +387,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.19999999999999998,
- "cost_per_1m_out": 1.1,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 0.86,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 48000,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -413,8 +439,8 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.38,
- "cost_per_1m_out": 1.53,
+ "cost_per_1m_in": 0.35,
+ "cost_per_1m_out": 1.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -595,10 +621,10 @@
{
"id": "x-ai/grok-3-mini",
"name": "xAI: Grok 3 Mini",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 0.5,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 4,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.075,
+ "cost_per_1m_out_cached": 0.15,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,
@@ -673,8 +699,8 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.1799999999999997,
+ "cost_per_1m_in": 0.7,
+ "cost_per_1m_out": 2.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
@@ -829,12 +855,12 @@
{
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen: Qwen3 30B A3B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.09,
+ "cost_per_1m_out": 0.44999999999999996,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 4000,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -855,12 +881,12 @@
{
"id": "qwen/qwen3-32b",
"name": "Qwen: Qwen3 32B",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 0.7999999999999999,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 0.5700000000000001,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 16384,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -972,10 +998,10 @@
{
"id": "x-ai/grok-3-mini-beta",
"name": "xAI: Grok 3 Mini Beta",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 0.5,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 4,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.075,
+ "cost_per_1m_out_cached": 0.15,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,
@@ -1011,12 +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": 0.15,
+ "cost_per_1m_out": 0.85,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1048576,
- "default_max_tokens": 524288,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1047,19 +1073,6 @@
"has_reasoning_efforts": false,
"supports_attachments": true
},
- {
- "id": "google/gemini-2.5-pro-exp-03-25",
- "name": "Google: Gemini 2.5 Pro Experimental",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 1048576,
- "default_max_tokens": 32767,
- "can_reason": false,
- "has_reasoning_efforts": false,
- "supports_attachments": true
- },
{
"id": "deepseek/deepseek-chat-v3-0324:free",
"name": "DeepSeek: DeepSeek V3 0324 (free)",
@@ -1268,19 +1281,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "id": "deepseek/deepseek-r1-distill-llama-70b",
- "name": "DeepSeek: R1 Distill Llama 70B",
- "cost_per_1m_in": 0.75,
- "cost_per_1m_out": 0.9900000000000001,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 65536,
- "can_reason": true,
- "has_reasoning_efforts": false,
- "supports_attachments": false
- },
{
"id": "deepseek/deepseek-r1",
"name": "DeepSeek: R1",
@@ -1310,12 +1310,12 @@
{
"id": "deepseek/deepseek-chat",
"name": "DeepSeek: DeepSeek V3",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 1.3,
+ "cost_per_1m_in": 0.8999999999999999,
+ "cost_per_1m_out": 0.8999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 64000,
- "default_max_tokens": 8000,
+ "context_window": 131072,
+ "default_max_tokens": 13107,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1366,8 +1366,8 @@
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 128000,
- "default_max_tokens": 2014,
+ "context_window": 65536,
+ "default_max_tokens": 6553,
"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": 0.039,
- "cost_per_1m_out": 0.12,
+ "cost_per_1m_in": 0.12,
+ "cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 4096,
+ "default_max_tokens": 65536,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1483,15 +1483,15 @@
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 32768,
- "default_max_tokens": 3276,
+ "context_window": 32000,
+ "default_max_tokens": 16000,
"can_reason": false,
"has_reasoning_efforts": false,
"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,
@@ -1607,10 +1607,10 @@
"supports_attachments": false
},
{
- "id": "cohere/command-r-plus-08-2024",
- "name": "Cohere: Command R+ (08-2024)",
- "cost_per_1m_in": 2.5,
- "cost_per_1m_out": 10,
+ "id": "cohere/command-r-08-2024",
+ "name": "Cohere: Command R (08-2024)",
+ "cost_per_1m_in": 0.15,
+ "cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
@@ -1620,10 +1620,10 @@
"supports_attachments": false
},
{
- "id": "cohere/command-r-08-2024",
- "name": "Cohere: Command R (08-2024)",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.6,
+ "id": "cohere/command-r-plus-08-2024",
+ "name": "Cohere: Command R+ (08-2024)",
+ "cost_per_1m_in": 2.5,
+ "cost_per_1m_out": 10,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
@@ -1645,6 +1645,19 @@
"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)",
@@ -1658,19 +1671,6 @@
"has_reasoning_efforts": false,
"supports_attachments": true
},
- {
- "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_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 8192,
- "can_reason": false,
- "has_reasoning_efforts": false,
- "supports_attachments": false
- },
{
"id": "meta-llama/llama-3.1-405b-instruct",
"name": "Meta: Llama 3.1 405B Instruct",
@@ -1697,6 +1697,19 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
+ {
+ "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_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 131072,
+ "default_max_tokens": 8192,
+ "can_reason": false,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
{
"id": "mistralai/mistral-nemo",
"name": "Mistral: Mistral Nemo",
@@ -1827,6 +1840,19 @@
"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",
@@ -1854,17 +1880,17 @@
"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",
@@ -1879,19 +1905,6 @@
"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",
@@ -1906,27 +1919,27 @@
"supports_attachments": false
},
{
- "id": "google/gemini-pro-1.5",
- "name": "Google: Gemini 1.5 Pro",
- "cost_per_1m_in": 1.25,
- "cost_per_1m_out": 5,
+ "id": "openai/gpt-4-turbo",
+ "name": "OpenAI: GPT-4 Turbo",
+ "cost_per_1m_in": 10,
+ "cost_per_1m_out": 30,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 2000000,
- "default_max_tokens": 4096,
+ "context_window": 128000,
+ "default_max_tokens": 2048,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
},
{
- "id": "openai/gpt-4-turbo",
- "name": "OpenAI: GPT-4 Turbo",
- "cost_per_1m_in": 10,
- "cost_per_1m_out": 30,
+ "id": "google/gemini-pro-1.5",
+ "name": "Google: Gemini 1.5 Pro",
+ "cost_per_1m_in": 1.25,
+ "cost_per_1m_out": 5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 128000,
- "default_max_tokens": 2048,
+ "context_window": 2000000,
+ "default_max_tokens": 4096,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -2023,26 +2036,26 @@
"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,
@@ -2114,13 +2127,13 @@
"supports_attachments": false
},
{
- "id": "openai/gpt-3.5-turbo",
- "name": "OpenAI: GPT-3.5 Turbo",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 1.5,
+ "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,
"cost_per_1m_out_cached": 0,
- "context_window": 16385,
+ "context_window": 8191,
"default_max_tokens": 2048,
"can_reason": false,
"has_reasoning_efforts": false,
@@ -2140,13 +2153,13 @@
"supports_attachments": false
},
{
- "id": "openai/gpt-4-0314",
- "name": "OpenAI: GPT-4 (older v0314)",
- "cost_per_1m_in": 30,
- "cost_per_1m_out": 60,
+ "id": "openai/gpt-3.5-turbo",
+ "name": "OpenAI: GPT-3.5 Turbo",
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 1.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 8191,
+ "context_window": 16385,
"default_max_tokens": 2048,
"can_reason": false,
"has_reasoning_efforts": false,