@@ -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,
@@ -197,7 +197,7 @@
"cost_per_1m_in_cached": 18.75,
"cost_per_1m_out_cached": 1.5,
"context_window": 200000,
- "default_max_tokens": 20000,
+ "default_max_tokens": 16000,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -371,19 +371,6 @@
"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-1.5-8b",
"name": "Google: Gemini 1.5 Flash 8B",
@@ -483,7 +470,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1048576,
- "default_max_tokens": 32768,
+ "default_max_tokens": 32767,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -496,7 +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
@@ -621,12 +608,12 @@
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0.39999999999999997,
- "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
@@ -660,12 +647,12 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.04,
- "cost_per_1m_out": 0.12,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.39,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -699,12 +686,12 @@
{
"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": 0.22,
+ "cost_per_1m_out": 0.88,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1048576,
- "default_max_tokens": 8192,
+ "default_max_tokens": 104857,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1138,19 +1125,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "id": "mistralai/pixtral-12b",
- "name": "Mistral: Pixtral 12B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.15,
- "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": true
- },
{
"id": "mistralai/pixtral-large-2411",
"name": "Mistral: Pixtral Large 2411",
@@ -1242,19 +1216,6 @@
"has_reasoning_efforts": true,
"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": true,
- "supports_attachments": false
- },
{
"id": "nousresearch/hermes-4-70b",
"name": "Nous: Hermes 4 70B",
@@ -1560,9 +1521,9 @@
"cost_per_1m_in": 0.25,
"cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.024999999999999998,
+ "cost_per_1m_out_cached": 0.03,
"context_window": 400000,
- "default_max_tokens": 64000,
+ "default_max_tokens": 40000,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -1573,9 +1534,9 @@
"cost_per_1m_in": 0.049999999999999996,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.01,
+ "cost_per_1m_out_cached": 0.005,
"context_window": 400000,
- "default_max_tokens": 40000,
+ "default_max_tokens": 64000,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -1596,12 +1557,12 @@
{
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
- "cost_per_1m_in": 0.04,
- "cost_per_1m_out": 0.15,
+ "cost_per_1m_in": 0.049999999999999996,
+ "cost_per_1m_out": 0.19999999999999998,
"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": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -1843,8 +1804,8 @@
{
"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": 0.08,
+ "cost_per_1m_out": 0.28,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -1856,12 +1817,12 @@
{
"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": 0.07,
+ "cost_per_1m_out": 0.28,
"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
@@ -1869,12 +1830,12 @@
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.08,
+ "cost_per_1m_out": 0.29,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 65536,
+ "default_max_tokens": 131072,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -1882,12 +1843,12 @@
{
"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
@@ -1921,12 +1882,12 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.29,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.25,
+ "cost_per_1m_out": 1,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 32768,
+ "default_max_tokens": 131072,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1986,12 +1947,12 @@
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen: Qwen3 Next 80B A3B Instruct",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.7999999999999999,
"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
@@ -2012,8 +1973,21 @@
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 1.5,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 131072,
+ "default_max_tokens": 16384,
+ "can_reason": false,
+ "has_reasoning_efforts": false,
+ "supports_attachments": true
+ },
+ {
+ "id": "qwen/qwen3-vl-235b-a22b-thinking",
+ "name": "Qwen: Qwen3 VL 235B A22B Thinking",
"cost_per_1m_in": 0.7,
- "cost_per_1m_out": 2.8,
+ "cost_per_1m_out": 8.399999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2065,7 +2039,7 @@
"id": "alibaba/tongyi-deepresearch-30b-a3b",
"name": "Tongyi DeepResearch 30B A3B",
"cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.44999999999999996,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2129,12 +2103,12 @@
{
"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
@@ -2142,10 +2116,10 @@
{
"id": "x-ai/grok-3",
"name": "xAI: Grok 3",
- "cost_per_1m_in": 5,
- "cost_per_1m_out": 25,
+ "cost_per_1m_in": 3,
+ "cost_per_1m_out": 15,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 1.25,
+ "cost_per_1m_out_cached": 0.75,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,
@@ -2155,10 +2129,10 @@
{
"id": "x-ai/grok-3-beta",
"name": "xAI: Grok 3 Beta",
- "cost_per_1m_in": 5,
- "cost_per_1m_out": 25,
+ "cost_per_1m_in": 3,
+ "cost_per_1m_out": 15,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 1.25,
+ "cost_per_1m_out_cached": 0.75,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,
@@ -2168,10 +2142,10 @@
{
"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,
@@ -2181,10 +2155,10 @@
{
"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,