@@ -8,18 +8,57 @@
"default_small_model_id": "anthropic/claude-3.5-haiku",
"models": [
{
- "id": "meituan/longcat-flash-chat",
- "name": "Meituan: LongCat Flash Chat",
- "cost_per_1m_in": 0.24999987999999998,
- "cost_per_1m_out": 0.999999888,
+ "id": "qwen/qwen3-next-80b-a3b-thinking",
+ "name": "Qwen: Qwen3 Next 80B A3B Thinking",
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
+ "context_window": 262144,
+ "default_max_tokens": 16384,
+ "can_reason": true,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
+ {
+ "id": "qwen/qwen3-next-80b-a3b-instruct",
+ "name": "Qwen: Qwen3 Next 80B A3B Instruct",
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 1.4,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 262144,
+ "default_max_tokens": 26214,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
},
+ {
+ "id": "qwen/qwen-plus-2025-07-28",
+ "name": "Qwen: Qwen Plus 0728",
+ "cost_per_1m_in": 0.39999999999999997,
+ "cost_per_1m_out": 1.2,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 1000000,
+ "default_max_tokens": 16384,
+ "can_reason": false,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
+ {
+ "id": "qwen/qwen-plus-2025-07-28:thinking",
+ "name": "Qwen: Qwen Plus 0728 (thinking)",
+ "cost_per_1m_in": 0.39999999999999997,
+ "cost_per_1m_out": 4,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 1000000,
+ "default_max_tokens": 16384,
+ "can_reason": true,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
{
"id": "nvidia/nemotron-nano-9b-v2:free",
"name": "NVIDIA: Nemotron Nano 9B V2 (free)",
@@ -127,12 +166,12 @@
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.08967387,
- "cost_per_1m_out": 0.358695612,
+ "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,
- "default_max_tokens": 131072,
+ "default_max_tokens": 26214,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -163,6 +202,19 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
+ {
+ "id": "nousresearch/hermes-4-405b",
+ "name": "Nous: Hermes 4 405B",
+ "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": true,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
{
"id": "deepseek/deepseek-chat-v3.1:free",
"name": "DeepSeek: DeepSeek V3.1 (free)",
@@ -218,12 +270,12 @@
{
"id": "z-ai/glm-4.5v",
"name": "Z.AI: GLM 4.5V",
- "cost_per_1m_in": 0.5,
+ "cost_per_1m_in": 0.6,
"cost_per_1m_out": 1.7999999999999998,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.11,
"context_window": 65536,
- "default_max_tokens": 32768,
+ "default_max_tokens": 8192,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -296,12 +348,12 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.6,
+ "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,
- "default_max_tokens": 16384,
+ "default_max_tokens": 13107,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -309,12 +361,12 @@
{
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
- "cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.19999999999999998,
+ "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": 16384,
+ "default_max_tokens": 13107,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -348,8 +400,8 @@
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.07065213999999999,
+ "cost_per_1m_out": 0.282608664,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -374,12 +426,12 @@
{
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
- "cost_per_1m_in": 0.41249980199999997,
- "cost_per_1m_out": 1.6499998152000002,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 2.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 49152,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -452,8 +504,8 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.44999999999999996,
- "cost_per_1m_out": 1.7999999999999998,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 1.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -478,7 +530,7 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.19999999999999998,
+ "cost_per_1m_in": 0.13,
"cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
@@ -504,12 +556,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.4,
+ "cost_per_1m_in": 0.58,
+ "cost_per_1m_out": 2.29,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 65536,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -634,10 +686,10 @@
{
"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,
@@ -664,7 +716,7 @@
"cost_per_1m_out": 1.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 40000,
+ "context_window": 40960,
"default_max_tokens": 20000,
"can_reason": true,
"has_reasoning_efforts": false,
@@ -712,12 +764,12 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.7,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 2.5500000000000003,
+ "cost_per_1m_out": 5.95,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 81920,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -868,12 +920,12 @@
{
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen: Qwen3 30B A3B",
- "cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.44999999999999996,
+ "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": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 4000,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -998,10 +1050,10 @@
{
"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,
@@ -1159,7 +1211,7 @@
"cost_per_1m_in_cached": 3.75,
"cost_per_1m_out_cached": 0.3,
"context_window": 200000,
- "default_max_tokens": 32000,
+ "default_max_tokens": 64000,
"can_reason": true,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1366,8 +1418,8 @@
"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 +1427,12 @@
{
"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": 0.09999999999999999,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 4096,
+ "default_max_tokens": 13107,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1490,8 +1542,8 @@
"supports_attachments": false
},
{
- "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,
@@ -1503,8 +1555,8 @@
"supports_attachments": true
},
{
- "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,
@@ -1520,8 +1572,8 @@
"name": "Anthropic: Claude 3.5 Sonnet",
"cost_per_1m_in": 3,
"cost_per_1m_out": 15,
- "cost_per_1m_in_cached": 3.75,
- "cost_per_1m_out_cached": 0.3,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
"context_window": 200000,
"default_max_tokens": 4096,
"can_reason": false,
@@ -1645,6 +1697,19 @@
"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)",
@@ -1674,12 +1739,12 @@
{
"id": "meta-llama/llama-3.1-405b-instruct",
"name": "Meta: Llama 3.1 405B Instruct",
- "cost_per_1m_in": 0.7999999999999999,
- "cost_per_1m_out": 0.7999999999999999,
+ "cost_per_1m_in": 3,
+ "cost_per_1m_out": 3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 32768,
- "default_max_tokens": 8192,
+ "context_window": 131072,
+ "default_max_tokens": 13107,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1687,12 +1752,12 @@
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0.22999999999999998,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.28,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false