@@ -129,8 +129,8 @@
"name": "Anthropic: Claude 3.5 Sonnet",
"cost_per_1m_in": 3,
"cost_per_1m_out": 15,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_in_cached": 3.75,
+ "cost_per_1m_out_cached": 0.3,
"context_window": 200000,
"default_max_tokens": 4096,
"can_reason": false,
@@ -388,11 +388,11 @@
"id": "deepseek/deepseek-r1",
"name": "DeepSeek: R1",
"cost_per_1m_in": 0.7,
- "cost_per_1m_out": 2.4,
+ "cost_per_1m_out": 2.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 163840,
- "default_max_tokens": 81920,
+ "context_window": 64000,
+ "default_max_tokens": 8000,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -410,19 +410,6 @@
"has_reasoning_efforts": true,
"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": true,
- "supports_attachments": false
- },
{
"id": "google/gemini-flash-1.5",
"name": "Google: Gemini 1.5 Flash ",
@@ -454,8 +441,8 @@
"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,
+ "cost_per_1m_in_cached": 2.875,
+ "cost_per_1m_out_cached": 0.625,
"context_window": 2000000,
"default_max_tokens": 4096,
"can_reason": false,
@@ -606,23 +593,23 @@
"supports_attachments": false
},
{
- "id": "meituan/longcat-flash-chat",
- "name": "Meituan: LongCat Flash Chat",
- "cost_per_1m_in": 0.12,
- "cost_per_1m_out": 0.6,
+ "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": 131072,
- "default_max_tokens": 13107,
+ "context_window": 8192,
+ "default_max_tokens": 8192,
"can_reason": false,
"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,
+ "id": "meta-llama/llama-3-8b-instruct",
+ "name": "Meta: Llama 3 8B Instruct",
+ "cost_per_1m_in": 0.03,
+ "cost_per_1m_out": 0.06,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 8192,
@@ -647,8 +634,8 @@
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0.88,
- "cost_per_1m_out": 0.88,
+ "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": 131072,
@@ -660,8 +647,8 @@
{
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Meta: Llama 3.1 8B Instruct",
- "cost_per_1m_in": 0.02,
- "cost_per_1m_out": 0.03,
+ "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,
@@ -686,12 +673,12 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.12,
- "cost_per_1m_out": 0.3,
+ "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": 65536,
+ "default_max_tokens": 13107,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -725,12 +712,12 @@
{
"id": "meta-llama/llama-4-maverick",
"name": "Meta: Llama 4 Maverick",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.85,
+ "cost_per_1m_in": 0.18,
+ "cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1048576,
- "default_max_tokens": 8192,
+ "default_max_tokens": 524288,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -751,12 +738,12 @@
{
"id": "meta-llama/llama-4-scout",
"name": "Meta: Llama 4 Scout",
- "cost_per_1m_in": 0.25,
- "cost_per_1m_out": 0.7,
+ "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": 1310720,
- "default_max_tokens": 4096,
+ "context_window": 1048576,
+ "default_max_tokens": 104857,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1154,12 +1141,12 @@
{
"id": "mistralai/mixtral-8x7b-instruct",
"name": "Mistral: Mixtral 8x7B Instruct",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 0.6,
+ "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": 32768,
- "default_max_tokens": 1024,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1609,8 +1596,8 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.49,
+ "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,
@@ -1843,8 +1830,8 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.12,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.09999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -1856,12 +1843,12 @@
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen: Qwen3 235B A22B Thinking 2507",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.39,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.6,
"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": true,
"supports_attachments": false
@@ -1895,12 +1882,12 @@
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.08,
- "cost_per_1m_out": 0.29,
+ "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": true,
"supports_attachments": false
@@ -1908,12 +1895,12 @@
{
"id": "qwen/qwen3-32b",
"name": "Qwen: Qwen3 32B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.5,
+ "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": 4000,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -1947,12 +1934,12 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.22,
- "cost_per_1m_out": 0.95,
+ "cost_per_1m_in": 0.29,
+ "cost_per_1m_out": 1.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 26214,
+ "default_max_tokens": 32768,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -2012,8 +1999,8 @@
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen: Qwen3 Next 80B A3B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.7999999999999999,
+ "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,
@@ -2103,12 +2090,12 @@
{
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 2.2,
+ "cost_per_1m_in": 0.41,
+ "cost_per_1m_out": 1.6500000000000001,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.11,
+ "cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 48000,
+ "default_max_tokens": 13107,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -2142,12 +2129,12 @@
{
"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": true,
"supports_attachments": true
@@ -2155,10 +2142,10 @@
{
"id": "x-ai/grok-3",
"name": "xAI: Grok 3",
- "cost_per_1m_in": 3,
- "cost_per_1m_out": 15,
+ "cost_per_1m_in": 5,
+ "cost_per_1m_out": 25,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.75,
+ "cost_per_1m_out_cached": 1.25,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,
@@ -2168,10 +2155,10 @@
{
"id": "x-ai/grok-3-beta",
"name": "xAI: Grok 3 Beta",
- "cost_per_1m_in": 3,
- "cost_per_1m_out": 15,
+ "cost_per_1m_in": 5,
+ "cost_per_1m_out": 25,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.75,
+ "cost_per_1m_out_cached": 1.25,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,