Current section
Files
Jump to
Current section
Files
priv/models/nearai.json
[
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
"input_cost": 0.15,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen3 30B-A3B Instruct 2507",
"output_cost": 0.55,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-07-29"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 256000,
"dialect": "openai_completions",
"id": "Qwen/Qwen3-VL-30B-A3B-Instruct",
"input_cost": 0.15,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 32768,
"name": "Qwen3-VL 30B-A3B Instruct",
"output_cost": 0.55,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-09-23"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "Qwen/Qwen3.5-122B-A10B",
"input_cost": 0.4,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen3.5 122B-A10B",
"output_cost": 3.2,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-02-23"
},
{
"cache_read_cost": 0.056,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "Qwen/Qwen3.6-35B-A3B-FP8",
"input_cost": 0.17,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen 3.6 35B A3B FP8",
"output_cost": 1.1,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-04-17"
},
{
"cache_read_cost": 0.1,
"cache_write_cost": 1.25,
"context_size": 200000,
"dialect": "openai_completions",
"id": "anthropic/claude-haiku-4-5",
"input_cost": 1,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 64000,
"name": "Claude Haiku 4.5 (latest)",
"output_cost": 5,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-10-15"
},
{
"cache_read_cost": 0.5,
"cache_write_cost": 6.25,
"context_size": 200000,
"dialect": "openai_completions",
"id": "anthropic/claude-opus-4-6",
"input_cost": 5,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 128000,
"name": "Claude Opus 4.6",
"output_cost": 25,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-02-05"
},
{
"cache_read_cost": 0.5,
"cache_write_cost": 6.25,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "anthropic/claude-opus-4-7",
"input_cost": 5,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 128000,
"name": "Claude Opus 4.7",
"output_cost": 25,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-04-16"
},
{
"cache_read_cost": 0.3,
"cache_write_cost": 3.75,
"context_size": 200000,
"dialect": "openai_completions",
"id": "anthropic/claude-sonnet-4-5",
"input_cost": 3,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 64000,
"name": "Claude Sonnet 4.5 (latest)",
"output_cost": 15.5,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-09-29"
},
{
"cache_read_cost": 0.3,
"cache_write_cost": 3.75,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "anthropic/claude-sonnet-4-6",
"input_cost": 3,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 64000,
"name": "Claude Sonnet 4.6",
"output_cost": 15,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-02-17"
},
{
"cache_read_cost": 0.03,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "google/gemini-2.5-flash",
"input_cost": 0.3,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 65536,
"name": "Gemini 2.5 Flash",
"output_cost": 2.5,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-03-20"
},
{
"cache_read_cost": 0.01,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "google/gemini-2.5-flash-lite",
"input_cost": 0.1,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 65536,
"name": "Gemini 2.5 Flash-Lite",
"output_cost": 0.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-06-17"
},
{
"cache_read_cost": 0.125,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "google/gemini-2.5-pro",
"input_cost": 1.25,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 65536,
"name": "Gemini 2.5 Pro",
"output_cost": 10,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-03-20"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "google/gemini-3-pro",
"input_cost": 1.25,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 65536,
"name": "Gemini 3 Pro Preview",
"output_cost": 15,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-11-18"
},
{
"cache_read_cost": 0.025,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "google/gemini-3.1-flash-lite",
"input_cost": 0.25,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 65536,
"name": "Gemini 3.1 Flash Lite",
"output_cost": 1.5,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-05-07"
},
{
"cache_read_cost": 0.15,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "google/gemini-3.5-flash",
"input_cost": 1.5,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 65536,
"name": "Gemini 3.5 Flash",
"output_cost": 9,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-05-19"
},
{
"cache_read_cost": 0.026,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "google/gemma-4-31B-it",
"input_cost": 0.13,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Gemma 4 31B IT",
"output_cost": 0.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-04-02"
},
{
"cache_read_cost": 0.5,
"cache_write_cost": 0,
"context_size": 1047576,
"dialect": "openai_completions",
"id": "openai/gpt-4.1",
"input_cost": 2,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 32768,
"name": "GPT-4.1",
"output_cost": 8,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-04-14"
},
{
"cache_read_cost": 0.1,
"cache_write_cost": 0,
"context_size": 1047576,
"dialect": "openai_completions",
"id": "openai/gpt-4.1-mini",
"input_cost": 0.4,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 32768,
"name": "GPT-4.1 mini",
"output_cost": 1.6,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-04-14"
},
{
"cache_read_cost": 0.025,
"cache_write_cost": 0,
"context_size": 1047576,
"dialect": "openai_completions",
"id": "openai/gpt-4.1-nano",
"input_cost": 0.1,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 32768,
"name": "GPT-4.1 nano",
"output_cost": 0.4,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-04-14"
},
{
"cache_read_cost": 0.125,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5",
"input_cost": 1.25,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5",
"output_cost": 10,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-08-07"
},
{
"cache_read_cost": 0.025,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5-mini",
"input_cost": 0.25,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5 Mini",
"output_cost": 2,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-08-07"
},
{
"cache_read_cost": 0.005,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5-nano",
"input_cost": 0.05,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5 Nano",
"output_cost": 0.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-08-07"
},
{
"cache_read_cost": 0.125,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5.1",
"input_cost": 1.25,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5.1",
"output_cost": 10,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-11-13"
},
{
"cache_read_cost": 0.18,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5.2",
"input_cost": 1.8,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5.2",
"output_cost": 15.5,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-12-11"
},
{
"cache_read_cost": 0.25,
"cache_write_cost": 0,
"context_size": 1050000,
"dialect": "openai_completions",
"id": "openai/gpt-5.4",
"input_cost": 2.5,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 128000,
"name": "GPT-5.4",
"output_cost": 15,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-03-05"
},
{
"cache_read_cost": 0.075,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5.4-mini",
"input_cost": 0.75,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5.4 mini",
"output_cost": 4.5,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-03-17"
},
{
"cache_read_cost": 0.02,
"cache_write_cost": 0,
"context_size": 400000,
"dialect": "openai_completions",
"id": "openai/gpt-5.4-nano",
"input_cost": 0.2,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 128000,
"name": "GPT-5.4 nano",
"output_cost": 1.25,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-03-17"
},
{
"cache_read_cost": 0.5,
"cache_write_cost": 0,
"context_size": 1050000,
"dialect": "openai_completions",
"id": "openai/gpt-5.5",
"input_cost": 5,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 128000,
"name": "GPT-5.5",
"output_cost": 30,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-04-23"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131000,
"dialect": "openai_completions",
"id": "openai/gpt-oss-120b",
"input_cost": 0.15,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "GPT-OSS 120B",
"output_cost": 0.55,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-08-05"
},
{
"cache_read_cost": 0.5,
"cache_write_cost": 0,
"context_size": 200000,
"dialect": "openai_completions",
"id": "openai/o3",
"input_cost": 2,
"input_modalities": [
"text",
"image",
"pdf"
],
"max_output_tokens": 100000,
"name": "o3",
"output_cost": 8,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04-16"
},
{
"cache_read_cost": 0.55,
"cache_write_cost": 0,
"context_size": 200000,
"dialect": "openai_completions",
"id": "openai/o3-mini",
"input_cost": 1.1,
"input_modalities": [
"text"
],
"max_output_tokens": 100000,
"name": "o3-mini",
"output_cost": 4.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2024-12-20"
},
{
"cache_read_cost": 0.275,
"cache_write_cost": 0,
"context_size": 200000,
"dialect": "openai_completions",
"id": "openai/o4-mini",
"input_cost": 1.1,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 100000,
"name": "o4-mini",
"output_cost": 4.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04-16"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 202752,
"dialect": "openai_completions",
"id": "zai-org/GLM-5.1-FP8",
"input_cost": 0.85,
"input_modalities": [
"text"
],
"max_output_tokens": 131072,
"name": "GLM-5.1 FP8",
"output_cost": 3.3,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-03-27"
}
]