@@ -164,7 +164,7 @@
"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",
@@ -605,11 +605,11 @@
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek: DeepSeek V3.2",
"cost_per_1m_in": 0.26,
- "cost_per_1m_out": 0.38,
+ "cost_per_1m_out": 0.39,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.13,
"context_window": 163840,
- "default_max_tokens": 32768,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -661,12 +661,31 @@
{
"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": 0.5,
+ "cost_per_1m_out": 2.1799999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.35,
+ "cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "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": 0.11,
+ "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",
@@ -682,7 +701,7 @@
"name": "Google: Gemini 2.0 Flash",
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
- "cost_per_1m_in_cached": 0.08333333333333334,
+ "cost_per_1m_in_cached": 0.08333333333333333,
"cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 1048576,
"default_max_tokens": 4096,
@@ -693,10 +712,10 @@
{
"id": "google/gemini-2.0-flash-exp:free",
"name": "Google: Gemini 2.0 Flash Experimental (free)",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in_cached": 0.08333333333333333,
+ "cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 1048576,
"default_max_tokens": 4096,
"can_reason": false,
@@ -721,7 +740,7 @@
"name": "Google: Gemini 2.5 Flash",
"cost_per_1m_in": 0.3,
"cost_per_1m_out": 2.5,
- "cost_per_1m_in_cached": 0.08333333333333334,
+ "cost_per_1m_in_cached": 0.08333333333333333,
"cost_per_1m_out_cached": 0.03,
"context_window": 1048576,
"default_max_tokens": 32767,
@@ -740,7 +759,7 @@
"name": "Google: Gemini 2.5 Flash Lite",
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
- "cost_per_1m_in_cached": 0.08333333333333334,
+ "cost_per_1m_in_cached": 0.08333333333333333,
"cost_per_1m_out_cached": 0.01,
"context_window": 1048576,
"default_max_tokens": 32767,
@@ -759,7 +778,7 @@
"name": "Google: Gemini 2.5 Flash Lite Preview 09-2025",
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
- "cost_per_1m_in_cached": 0.08333333333333334,
+ "cost_per_1m_in_cached": 0.08333333333333333,
"cost_per_1m_out_cached": 0.01,
"context_window": 1048576,
"default_max_tokens": 32768,
@@ -778,7 +797,7 @@
"name": "Google: Gemini 2.5 Flash Preview 09-2025",
"cost_per_1m_in": 0.3,
"cost_per_1m_out": 2.5,
- "cost_per_1m_in_cached": 0.08333333333333334,
+ "cost_per_1m_in_cached": 0.08333333333333333,
"cost_per_1m_out_cached": 0.03,
"context_window": 1048576,
"default_max_tokens": 32767,
@@ -854,7 +873,7 @@
"name": "Google: Gemini 3 Flash Preview",
"cost_per_1m_in": 0.5,
"cost_per_1m_out": 3,
- "cost_per_1m_in_cached": 0,
+ "cost_per_1m_in_cached": 0.08333333333333333,
"cost_per_1m_out_cached": 0.049999999999999996,
"context_window": 1048576,
"default_max_tokens": 32767,
@@ -900,6 +919,19 @@
"supports_attachments": true,
"options": {}
},
+ {
+ "id": "google/gemma-3-27b-it:free",
+ "name": "Google: Gemma 3 27B (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": 128000,
+ "default_max_tokens": 12800,
+ "can_reason": false,
+ "supports_attachments": true,
+ "options": {}
+ },
{
"id": "inception/mercury",
"name": "Inception: Mercury",
@@ -942,8 +974,8 @@
{
"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,
@@ -972,8 +1004,8 @@
"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": 128000,
+ "default_max_tokens": 12800,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -981,12 +1013,12 @@
{
"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": {}
@@ -1007,10 +1039,10 @@
{
"id": "minimax/minimax-m2",
"name": "MiniMax: MiniMax M2",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 1.2,
- "cost_per_1m_in_cached": 0.375,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_in": 0.255,
+ "cost_per_1m_out": 1.02,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
"context_window": 204800,
"default_max_tokens": 65536,
"can_reason": true,
@@ -1028,10 +1060,10 @@
"name": "MiniMax: MiniMax M2.1",
"cost_per_1m_in": 0.3,
"cost_per_1m_out": 1.2,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_in_cached": 0.375,
+ "cost_per_1m_out_cached": 0.03,
"context_window": 204800,
- "default_max_tokens": 20480,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1277,16 +1309,16 @@
"options": {}
},
{
- "id": "mistralai/mistral-small-3.1-24b-instruct",
- "name": "Mistral: Mistral Small 3.1 24B",
- "cost_per_1m_in": 0.03,
- "cost_per_1m_out": 0.11,
+ "id": "mistralai/mistral-small-24b-instruct-2501",
+ "name": "Mistral: Mistral Small 3",
+ "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,
+ "context_window": 32768,
+ "default_max_tokens": 1024,
"can_reason": false,
- "supports_attachments": true,
+ "supports_attachments": false,
"options": {}
},
{
@@ -1305,12 +1337,12 @@
{
"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": {}
@@ -1396,12 +1428,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.4,
+ "cost_per_1m_in": 0.5700000000000001,
+ "cost_per_1m_out": 2.3,
"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,
"supports_attachments": false,
"options": {}
@@ -1610,6 +1642,25 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "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,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "openai/gpt-4-turbo",
"name": "OpenAI: GPT-4 Turbo",
@@ -1874,9 +1925,9 @@
"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,
"reasoning_levels": [
"low",
@@ -1893,9 +1944,9 @@
"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",
@@ -2041,7 +2092,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0.175,
"context_window": 128000,
- "default_max_tokens": 16000,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -2144,12 +2195,12 @@
{
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
- "cost_per_1m_in": 0.02,
- "cost_per_1m_out": 0.09999999999999999,
+ "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": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 13107,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2373,12 +2424,12 @@
{
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.52,
+ "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": {}
@@ -2521,12 +2572,12 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.09999999999999999,
+ "cost_per_1m_in": 0.08,
+ "cost_per_1m_out": 0.55,
"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": {}
@@ -2553,8 +2604,8 @@
{
"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": 0.09,
+ "cost_per_1m_out": 0.44999999999999996,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2642,12 +2693,12 @@
{
"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": 0.28,
"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": {}
@@ -2733,12 +2784,12 @@
{
"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": 0.09999999999999999,
+ "cost_per_1m_out": 0.7999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 26214,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2759,8 +2810,8 @@
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.2,
+ "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": 262144,
@@ -2788,34 +2839,15 @@
"supports_attachments": true,
"options": {}
},
- {
- "id": "qwen/qwen3-vl-235b-a22b-thinking",
- "name": "Qwen: Qwen3 VL 235B A22B Thinking",
- "cost_per_1m_in": 0.44999999999999996,
- "cost_per_1m_out": 3.5,
- "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",
- "cost_per_1m_in": 0.19999999999999998,
- "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": 128000,
- "default_max_tokens": 12800,
+ "context_window": 262144,
+ "default_max_tokens": 26214,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -2960,6 +2992,19 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "thedrummer/rocinante-12b",
+ "name": "TheDrummer: Rocinante 12B",
+ "cost_per_1m_in": 0.16999999999999998,
+ "cost_per_1m_out": 0.43,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 32768,
+ "default_max_tokens": 3276,
+ "can_reason": false,
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "thedrummer/unslopnemo-12b",
"name": "TheDrummer: UnslopNemo 12B",
@@ -2977,7 +3022,7 @@
"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,
@@ -2995,12 +3040,12 @@
{
"id": "xiaomi/mimo-v2-flash",
"name": "Xiaomi: MiMo-V2-Flash",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.09,
+ "cost_per_1m_out": 0.29,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 32768,
+ "default_max_tokens": 26214,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3051,7 +3096,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0.11,
"context_window": 131072,
- "default_max_tokens": 48000,
+ "default_max_tokens": 49152,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3198,12 +3243,12 @@
{
"id": "z-ai/glm-4.7-flash",
"name": "Z.AI: GLM 4.7 Flash",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.43,
+ "cost_per_1m_in": 0.07,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 202752,
- "default_max_tokens": 20275,
+ "cost_per_1m_out_cached": 0.01,
+ "context_window": 200000,
+ "default_max_tokens": 65550,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3243,10 +3288,10 @@
{
"id": "x-ai/grok-3-mini",
"name": "xAI: Grok 3 Mini",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 0.5,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 4,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.075,
+ "cost_per_1m_out_cached": 0.15,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,
@@ -3262,10 +3307,10 @@
{
"id": "x-ai/grok-3-mini-beta",
"name": "xAI: Grok 3 Mini Beta",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 0.5,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 4,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.075,
+ "cost_per_1m_out_cached": 0.15,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,