@@ -209,7 +209,7 @@
"cost_per_1m_in_cached": 3.75,
"cost_per_1m_out_cached": 0.3,
"context_window": 200000,
- "default_max_tokens": 64000,
+ "default_max_tokens": 32000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -361,7 +361,7 @@
"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,
"reasoning_levels": [
"low",
@@ -533,14 +533,14 @@
"options": {}
},
{
- "id": "deepseek/deepseek-chat-v3.1",
- "name": "DeepSeek: DeepSeek V3.1",
- "cost_per_1m_in": 0.21,
- "cost_per_1m_out": 0.7899999999999999,
+ "id": "deepseek/deepseek-chat-v3-0324",
+ "name": "DeepSeek: DeepSeek V3 0324",
+ "cost_per_1m_in": 0.77,
+ "cost_per_1m_out": 0.77,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.16799999999999998,
+ "cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -554,12 +554,12 @@
{
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek: DeepSeek V3.1 Terminus",
- "cost_per_1m_in": 0.22999999999999998,
- "cost_per_1m_out": 0.8999999999999999,
+ "cost_per_1m_in": 0.21,
+ "cost_per_1m_out": 0.7899999999999999,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.16799999999999998,
"context_window": 163840,
- "default_max_tokens": 81920,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -573,11 +573,11 @@
{
"id": "deepseek/deepseek-v3.1-terminus:exacto",
"name": "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.21,
+ "cost_per_1m_out": 0.7899999999999999,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
+ "cost_per_1m_out_cached": 0.16799999999999998,
+ "context_window": 163840,
"default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
@@ -592,12 +592,12 @@
{
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek: DeepSeek V3.2",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.26,
+ "cost_per_1m_out": 0.39,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.216,
+ "cost_per_1m_out_cached": 0.19999999999999998,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 32768,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -630,12 +630,12 @@
{
"id": "deepseek/deepseek-r1",
"name": "DeepSeek: R1",
- "cost_per_1m_in": 0.7,
- "cost_per_1m_out": 2.4,
+ "cost_per_1m_in": 0.56,
+ "cost_per_1m_out": 2,
"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,
"reasoning_levels": [
"low",
@@ -649,10 +649,10 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.56,
- "cost_per_1m_out": 2,
+ "cost_per_1m_in": 0.7999999999999999,
+ "cost_per_1m_out": 2.4,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.28,
+ "cost_per_1m_out_cached": 0,
"context_window": 163840,
"default_max_tokens": 16384,
"can_reason": true,
@@ -875,6 +875,19 @@
"supports_attachments": true,
"options": {}
},
+ {
+ "id": "google/gemma-3-27b-it",
+ "name": "Google: Gemma 3 27B",
+ "cost_per_1m_in": 0.04,
+ "cost_per_1m_out": 0.15,
+ "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",
@@ -909,7 +922,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 256000,
- "default_max_tokens": 16384,
+ "default_max_tokens": 16000,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -943,12 +956,12 @@
{
"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": 0.88,
+ "cost_per_1m_out": 0.88,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 8192,
+ "default_max_tokens": 13107,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -999,8 +1012,8 @@
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
+ "context_window": 65536,
+ "default_max_tokens": 6553,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1008,12 +1021,12 @@
{
"id": "meta-llama/llama-4-maverick",
"name": "Meta: Llama 4 Maverick",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 0.85,
+ "cost_per_1m_in": 0.35,
+ "cost_per_1m_out": 1.15,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 1048576,
- "default_max_tokens": 104857,
+ "context_window": 524288,
+ "default_max_tokens": 4096,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -1073,10 +1086,10 @@
{
"id": "minimax/minimax-m2",
"name": "MiniMax: MiniMax M2",
- "cost_per_1m_in": 0.255,
+ "cost_per_1m_in": 0.254,
"cost_per_1m_out": 1.02,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.1275,
+ "cost_per_1m_out_cached": 0.127,
"context_window": 262144,
"default_max_tokens": 26214,
"can_reason": true,
@@ -1154,6 +1167,19 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "mistralai/devstral-2512:free",
+ "name": "Mistral: Devstral 2 2512 (free)",
+ "cost_per_1m_in": 0,
+ "cost_per_1m_out": 0,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 262144,
+ "default_max_tokens": 26214,
+ "can_reason": false,
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "mistralai/devstral-medium",
"name": "Mistral: Devstral Medium",
@@ -1326,12 +1352,12 @@
{
"id": "mistralai/mistral-small-24b-instruct-2501",
"name": "Mistral: Mistral Small 3",
- "cost_per_1m_in": 0.7999999999999999,
- "cost_per_1m_out": 0.7999999999999999,
+ "cost_per_1m_in": 0.03,
+ "cost_per_1m_out": 0.11,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
- "default_max_tokens": 1024,
+ "default_max_tokens": 16384,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1456,10 +1482,10 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 1.15,
- "cost_per_1m_out": 8,
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.15,
+ "cost_per_1m_out_cached": 0.39999999999999997,
"context_window": 262144,
"default_max_tokens": 26214,
"can_reason": false,
@@ -1606,6 +1632,25 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "nousresearch/hermes-4-405b",
+ "name": "Nous: Hermes 4 405B",
+ "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": 131072,
+ "default_max_tokens": 65536,
+ "can_reason": true,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "openai/codex-mini",
"name": "OpenAI: Codex Mini",
@@ -1889,9 +1934,9 @@
"cost_per_1m_in": 0.25,
"cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 400000,
- "default_max_tokens": 40000,
+ "default_max_tokens": 64000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1908,9 +1953,9 @@
"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",
@@ -2113,7 +2158,7 @@
"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,
"reasoning_levels": [
"low",
@@ -2318,12 +2363,12 @@
{
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
- "cost_per_1m_in": 0.07,
- "cost_per_1m_out": 0.26,
+ "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": 32768,
- "default_max_tokens": 16384,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2472,12 +2517,12 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.19999999999999998,
- "cost_per_1m_out": 0.6,
+ "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": 26214,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2485,12 +2530,12 @@
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen: Qwen3 235B A22B Thinking 2507",
- "cost_per_1m_in": 0.65,
- "cost_per_1m_out": 3,
+ "cost_per_1m_in": 0.11,
+ "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,
"reasoning_levels": [
"low",
@@ -2504,12 +2549,12 @@
{
"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",
@@ -2593,8 +2638,8 @@
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
- "cost_per_1m_in": 0.06,
- "cost_per_1m_out": 0.25,
+ "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,
@@ -2606,12 +2651,12 @@
{
"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": 1.5,
+ "cost_per_1m_out": 7.5,
"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": {}
@@ -2690,8 +2735,8 @@
{
"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,
@@ -2703,8 +2748,8 @@
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 0.3,
+ "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,
@@ -2732,25 +2777,6 @@
"supports_attachments": true,
"options": {}
},
- {
- "id": "qwen/qwen3-vl-235b-a22b-thinking",
- "name": "Qwen: Qwen3 VL 235B A22B Thinking",
- "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,
- "default_max_tokens": 131072,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": true,
- "options": {}
- },
{
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen: Qwen3 VL 30B A3B Instruct",
@@ -2934,7 +2960,7 @@
"id": "alibaba/tongyi-deepresearch-30b-a3b",
"name": "Tongyi DeepResearch 30B A3B",
"cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_out": 0.44999999999999996,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2984,12 +3010,12 @@
{
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
- "cost_per_1m_in": 0.48,
- "cost_per_1m_out": 1.76,
+ "cost_per_1m_in": 0.35,
+ "cost_per_1m_out": 1.55,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.088,
+ "cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 49152,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3079,12 +3105,12 @@
{
"id": "z-ai/glm-4.6:exacto",
"name": "Z.AI: GLM 4.6 (exacto)",
- "cost_per_1m_in": 0.43,
- "cost_per_1m_out": 1.75,
+ "cost_per_1m_in": 0.44,
+ "cost_per_1m_out": 1.76,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.0799999993,
- "context_window": 202752,
- "default_max_tokens": 20275,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 204800,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -7,25 +7,6 @@
"default_large_model_id": "hf:zai-org/GLM-4.6",
"default_small_model_id": "hf:deepseek-ai/DeepSeek-V3.1-Terminus",
"models": [
- {
- "id": "hf:deepseek-ai/DeepSeek-R1",
- "name": "DeepSeek R1",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": false,
- "options": {}
- },
{
"id": "hf:deepseek-ai/DeepSeek-R1-0528",
"name": "DeepSeek R1 0528",
@@ -154,19 +135,6 @@
"supports_attachments": false,
"options": {}
},
- {
- "id": "hf:moonshotai/Kimi-K2-Instruct",
- "name": "Kimi K2 Instruct",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": false,
- "supports_attachments": false,
- "options": {}
- },
{
"id": "hf:moonshotai/Kimi-K2-Instruct-0905",
"name": "Kimi K2 Instruct 0905",
@@ -199,45 +167,6 @@
"supports_attachments": false,
"options": {}
},
- {
- "id": "hf:meta-llama/Llama-3.1-405B-Instruct",
- "name": "Llama 3.1 405B Instruct",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": false,
- "supports_attachments": false,
- "options": {}
- },
- {
- "id": "hf:meta-llama/Llama-3.1-70B-Instruct",
- "name": "Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": false,
- "supports_attachments": false,
- "options": {}
- },
- {
- "id": "hf:meta-llama/Llama-3.1-8B-Instruct",
- "name": "Llama 3.1 8B Instruct",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": false,
- "supports_attachments": false,
- "options": {}
- },
{
"id": "hf:meta-llama/Llama-3.3-70B-Instruct",
"name": "Llama 3.3 70B Instruct",
@@ -264,19 +193,6 @@
"supports_attachments": true,
"options": {}
},
- {
- "id": "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct",
- "name": "Llama 4 Scout 17B 16E Instruct",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 335872,
- "default_max_tokens": 33587,
- "can_reason": false,
- "supports_attachments": true,
- "options": {}
- },
{
"id": "hf:MiniMaxAI/MiniMax-M2",
"name": "MiniMax M2",