@@ -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,
@@ -220,8 +220,8 @@
"name": "Anthropic: Claude Sonnet 4.5",
"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": 1000000,
"default_max_tokens": 32000,
"can_reason": true,
@@ -296,12 +296,12 @@
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek: DeepSeek V3 0324",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 1.12,
+ "cost_per_1m_in": 0.28,
+ "cost_per_1m_out": 0.88,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 81920,
+ "default_max_tokens": 16384,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -335,8 +335,8 @@
{
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek: DeepSeek V3.1 Terminus",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 1,
+ "cost_per_1m_in": 0.22999999999999998,
+ "cost_per_1m_out": 0.8999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
@@ -349,11 +349,11 @@
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek: DeepSeek V3.2 Exp",
"cost_per_1m_in": 0.27,
- "cost_per_1m_out": 0.41,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 32768,
+ "default_max_tokens": 16384,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -374,12 +374,12 @@
{
"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": 16384,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -483,7 +483,7 @@
"cost_per_1m_in_cached": 0.3833,
"cost_per_1m_out_cached": 0.075,
"context_window": 1048576,
- "default_max_tokens": 32768,
+ "default_max_tokens": 32767,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -595,12 +595,12 @@
{
"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
@@ -621,12 +621,12 @@
{
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Meta: Llama 3.1 8B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.09999999999999999,
+ "cost_per_1m_in": 0.02,
+ "cost_per_1m_out": 0.03,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 4000,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -664,8 +664,8 @@
"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
@@ -1076,12 +1076,12 @@
{
"id": "mistralai/mistral-small-3.2-24b-instruct",
"name": "Mistral: Mistral Small 3.2 24B",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.06,
+ "cost_per_1m_out": 0.18,
"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": true
@@ -1167,12 +1167,12 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.39999999999999997,
+ "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,
- "default_max_tokens": 131072,
+ "default_max_tokens": 26214,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1242,19 +1242,6 @@
"has_reasoning_efforts": true,
"supports_attachments": false
},
- {
- "id": "nousresearch/hermes-4-70b",
- "name": "Nous: Hermes 4 70B",
- "cost_per_1m_in": 0.11,
- "cost_per_1m_out": 0.38,
- "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": "openai/codex-mini",
"name": "OpenAI: Codex Mini",
@@ -1596,12 +1583,12 @@
{
"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": 0.03,
+ "cost_per_1m_out": 0.14,
"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": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -1710,19 +1697,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "id": "qwen/qwq-32b",
- "name": "Qwen: QwQ 32B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.58,
- "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": "qwen/qwen-plus-2025-07-28",
"name": "Qwen: Qwen Plus 0728",
@@ -1843,12 +1817,12 @@
{
"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": 0.08,
+ "cost_per_1m_out": 0.28,
"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
@@ -1856,8 +1830,8 @@
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen: Qwen3 30B A3B Instruct 2507",
- "cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.08,
+ "cost_per_1m_out": 0.33,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -1869,12 +1843,12 @@
{
"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
@@ -1882,12 +1856,12 @@
{
"id": "qwen/qwen3-32b",
"name": "Qwen: Qwen3 32B",
- "cost_per_1m_in": 0.14,
- "cost_per_1m_out": 0.5700000000000001,
+ "cost_per_1m_in": 0.15,
+ "cost_per_1m_out": 0.5,
"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": true,
"supports_attachments": false
@@ -1908,8 +1882,8 @@
{
"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": 0.07,
+ "cost_per_1m_out": 0.27,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -1986,8 +1960,8 @@
{
"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": 0.15,
+ "cost_per_1m_out": 1.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2012,14 +1986,14 @@
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 0.7,
+ "cost_per_1m_out": 2.8,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
- "can_reason": false,
- "has_reasoning_efforts": false,
+ "default_max_tokens": 16384,
+ "can_reason": true,
+ "has_reasoning_efforts": true,
"supports_attachments": true
},
{
@@ -2116,12 +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": 0.35,
+ "cost_per_1m_out": 1.55,
"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": 65536,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -2158,7 +2132,7 @@
"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": 8192,
"can_reason": true,
@@ -2169,11 +2143,11 @@
"id": "z-ai/glm-4.6",
"name": "Z.AI: GLM 4.6",
"cost_per_1m_in": 0.6,
- "cost_per_1m_out": 2.2,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 204800,
- "default_max_tokens": 65536,
+ "default_max_tokens": 20480,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -2181,10 +2155,10 @@
{
"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,
@@ -2194,10 +2168,10 @@
{
"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,