{
"MiniMaxAI/MiniMax-M2.7": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 202752,
"cost": {
"cacheRead": 0.06,
"cacheWrite": 0,
"input": 0.3,
"output": 1.2
},
"id": "MiniMaxAI/MiniMax-M2.7",
"input": [
"text"
],
"maxTokens": 131072,
"name": "MiniMax-M2.7",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null,
"off": null
}
},
"MiniMaxAI/MiniMax-M3": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 524288,
"cost": {
"cacheRead": 0.06,
"cacheWrite": 0,
"input": 0.3,
"output": 1.2
},
"id": "MiniMaxAI/MiniMax-M3",
"input": [
"text",
"image"
],
"maxTokens": 250000,
"name": "MiniMax-M3",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 32768,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.3,
"output": 0.3
},
"id": "Qwen/Qwen2.5-7B-Instruct-Turbo",
"input": [
"text"
],
"maxTokens": 32768,
"name": "Qwen 2.5 7B Instruct Turbo",
"provider": "together",
"reasoning": false
},
"Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.2,
"output": 0.6
},
"id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
"input": [
"text"
],
"maxTokens": 262144,
"name": "Qwen3 235B A22B Instruct 2507 FP8",
"provider": "together",
"reasoning": false
},
"Qwen/Qwen3.5-397B-A17B": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.6,
"output": 3.6
},
"id": "Qwen/Qwen3.5-397B-A17B",
"input": [
"text",
"image"
],
"maxTokens": 130000,
"name": "Qwen3.5 397B A17B",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"Qwen/Qwen3.5-9B": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.17,
"output": 0.25
},
"id": "Qwen/Qwen3.5-9B",
"input": [
"text",
"image"
],
"maxTokens": 65536,
"name": "Qwen3.5 9B",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"Qwen/Qwen3.6-Plus": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 1000000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.5,
"output": 3
},
"id": "Qwen/Qwen3.6-Plus",
"input": [
"text"
],
"maxTokens": 500000,
"name": "Qwen3.6 Plus",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"Qwen/Qwen3.7-Max": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 1000000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 1.25,
"output": 3.75
},
"id": "Qwen/Qwen3.7-Max",
"input": [
"text"
],
"maxTokens": 500000,
"name": "Qwen3.7 Max",
"provider": "together",
"reasoning": false
},
"deepseek-ai/DeepSeek-V4-Pro": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": true,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 512000,
"cost": {
"cacheRead": 0.2,
"cacheWrite": 0,
"input": 1.74,
"output": 3.48
},
"id": "deepseek-ai/DeepSeek-V4-Pro",
"input": [
"text"
],
"maxTokens": 384000,
"name": "DeepSeek V4 Pro",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"high": "high",
"low": null,
"medium": null,
"minimal": null,
"xhigh": null
}
},
"essentialai/Rnj-1-Instruct": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 32768,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.15,
"output": 0.15
},
"id": "essentialai/Rnj-1-Instruct",
"input": [
"text"
],
"maxTokens": 32768,
"name": "Rnj-1 Instruct",
"provider": "together",
"reasoning": false
},
"google/gemma-4-31B-it": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.39,
"output": 0.97
},
"id": "google/gemma-4-31B-it",
"input": [
"text",
"image"
],
"maxTokens": 131072,
"name": "Gemma 4 31B Instruct",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 131072,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 1.04,
"output": 1.04
},
"id": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"input": [
"text"
],
"maxTokens": 131072,
"name": "Llama 3.3 70B",
"provider": "together",
"reasoning": false
},
"moonshotai/Kimi-K2.6": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0.2,
"cacheWrite": 0,
"input": 1.2,
"output": 4.5
},
"id": "moonshotai/Kimi-K2.6",
"input": [
"text",
"image"
],
"maxTokens": 131000,
"name": "Kimi K2.6",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"moonshotai/Kimi-K2.7-Code": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0.19,
"cacheWrite": 0,
"input": 0.95,
"output": 4
},
"id": "moonshotai/Kimi-K2.7-Code",
"input": [
"text"
],
"maxTokens": 131072,
"name": "Kimi K2.7 Code",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 512300,
"cost": {
"cacheRead": 0.2,
"cacheWrite": 0,
"input": 0.6,
"output": 3.6
},
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"input": [
"text"
],
"maxTokens": 512300,
"name": "Nemotron 3 Ultra 550B A55B",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"openai/gpt-oss-120b": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": true,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "openai"
},
"contextWindow": 131072,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.15,
"output": 0.6
},
"id": "openai/gpt-oss-120b",
"input": [
"text"
],
"maxTokens": 131072,
"name": "GPT OSS 120B",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"minimal": null,
"off": null
}
},
"openai/gpt-oss-20b": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": true,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "openai"
},
"contextWindow": 131072,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.05,
"output": 0.2
},
"id": "openai/gpt-oss-20b",
"input": [
"text"
],
"maxTokens": 131072,
"name": "GPT OSS 20B",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"minimal": null,
"off": null
}
},
"zai-org/GLM-5": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 202752,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 1,
"output": 3.2
},
"id": "zai-org/GLM-5",
"input": [
"text"
],
"maxTokens": 131072,
"name": "GLM-5",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"zai-org/GLM-5.1": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 202752,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 1.4,
"output": 4.4
},
"id": "zai-org/GLM-5.1",
"input": [
"text"
],
"maxTokens": 131072,
"name": "GLM-5.1",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
},
"zai-org/GLM-5.2": {
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false,
"thinkingFormat": "together"
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0.26,
"cacheWrite": 0,
"input": 1.4,
"output": 4.4
},
"id": "zai-org/GLM-5.2",
"input": [
"text"
],
"maxTokens": 164000,
"name": "GLM-5.2",
"provider": "together",
"reasoning": true,
"thinkingLevelMap": {
"low": null,
"medium": null,
"minimal": null
}
}
}