@@ -148,8 +148,8 @@
"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,
@@ -567,31 +567,12 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 1.75,
+ "cost_per_1m_in": 0.7999999999999999,
+ "cost_per_1m_out": 2.4,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 81920,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": false,
- "options": {}
- },
- {
- "id": "deepseek/deepseek-r1-distill-llama-70b",
- "name": "DeepSeek: R1 Distill Llama 70B",
- "cost_per_1m_in": 0.03,
- "cost_per_1m_out": 0.13,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -666,7 +647,7 @@
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0.18330000000000002,
- "cost_per_1m_out_cached": 0.01,
+ "cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 1048576,
"default_max_tokens": 32767,
"can_reason": true,
@@ -725,7 +706,7 @@
"cost_per_1m_in_cached": 0.3833,
"cost_per_1m_out_cached": 0.075,
"context_window": 1048576,
- "default_max_tokens": 32767,
+ "default_max_tokens": 32768,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -793,19 +774,6 @@
"supports_attachments": true,
"options": {}
},
- {
- "id": "google/gemma-3-27b-it",
- "name": "Google: Gemma 3 27B",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.52,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 96000,
- "default_max_tokens": 48000,
- "can_reason": false,
- "supports_attachments": true,
- "options": {}
- },
{
"id": "inception/mercury",
"name": "Inception: Mercury",
@@ -874,12 +842,12 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.59,
- "cost_per_1m_out": 0.7899999999999999,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.38,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 16384,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1340,12 +1308,12 @@
{
"id": "mistralai/mistral-small-3.2-24b-instruct",
"name": "Mistral: Mistral Small 3.2 24B",
- "cost_per_1m_in": 0.06,
- "cost_per_1m_out": 0.18,
+ "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": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 13107,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -1457,12 +1425,12 @@
{
"id": "moonshotai/kimi-k2-0905:exacto",
"name": "MoonshotAI: Kimi K2 0905 (exacto)",
- "cost_per_1m_in": 1,
- "cost_per_1m_out": 3,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 2.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 8192,
+ "default_max_tokens": 26214,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1922,9 +1890,9 @@
"cost_per_1m_in": 0.049999999999999996,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.005,
+ "cost_per_1m_out_cached": 0.01,
"context_window": 400000,
- "default_max_tokens": 64000,
+ "default_max_tokens": 40000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1957,12 +1925,12 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.14,
- "cost_per_1m_out": 0.95,
+ "cost_per_1m_in": 0.049999999999999996,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1977,11 +1945,11 @@
"id": "openai/gpt-oss-120b:exacto",
"name": "OpenAI: gpt-oss-120b (exacto)",
"cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.24,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1995,8 +1963,8 @@
{
"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": 0.03,
+ "cost_per_1m_out": 0.14,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2186,35 +2154,16 @@
{
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.12,
+ "cost_per_1m_out": 0.39,
"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,
"supports_attachments": false,
"options": {}
},
- {
- "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,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": false,
- "options": {}
- },
{
"id": "qwen/qwen-plus-2025-07-28",
"name": "Qwen: Qwen Plus 0728",
@@ -2340,13 +2289,19 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.35,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.22,
+ "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,
- "can_reason": false,
+ "can_reason": true,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
"supports_attachments": false,
"options": {}
},
@@ -2372,12 +2327,12 @@
{
"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,
"reasoning_levels": [
"low",
@@ -2404,12 +2359,12 @@
{
"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": 0.08,
+ "cost_per_1m_out": 0.29,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 26214,
+ "default_max_tokens": 131072,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2474,12 +2429,12 @@
{
"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": 131072,
+ "default_max_tokens": 32768,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2558,12 +2513,12 @@
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen: Qwen3 Next 80B A3B Instruct",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.5,
+ "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,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2571,12 +2526,12 @@
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.5,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 16384,
+ "context_window": 262144,
+ "default_max_tokens": 131072,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2606,6 +2561,19 @@
"supports_attachments": true,
"options": {}
},
+ {
+ "id": "qwen/qwen3-vl-30b-a3b-instruct",
+ "name": "Qwen: Qwen3 VL 30B A3B Instruct",
+ "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": 131072,
+ "can_reason": false,
+ "supports_attachments": true,
+ "options": {}
+ },
{
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"name": "Qwen: Qwen3 VL 30B A3B Thinking",
@@ -2776,7 +2744,7 @@
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
"cost_per_1m_in": 0.35,
- "cost_per_1m_out": 1.55,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2794,12 +2762,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.85,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 0.86,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 49152,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2851,12 +2819,12 @@
{
"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_in": 0.5,
+ "cost_per_1m_out": 1.9,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.11,
+ "cost_per_1m_out_cached": 0,
"context_window": 204800,
- "default_max_tokens": 65536,
+ "default_max_tokens": 102400,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2871,11 +2839,11 @@
"id": "z-ai/glm-4.6:exacto",
"name": "Z.AI: GLM 4.6 (exacto)",
"cost_per_1m_in": 0.6,
- "cost_per_1m_out": 1.9,
+ "cost_per_1m_out": 2.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 202752,
- "default_max_tokens": 20275,
+ "context_window": 200000,
+ "default_max_tokens": 64000,
"can_reason": true,
"reasoning_levels": [
"low",