{
    "$schema": "./provider-catalog.schema.json",
    "id": "prime-intellect",
    "displayName": "Prime Intellect",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.pinference.ai/api/v1",
        "apiKeyFallbackEnvVars": ["PRIME_API_KEY"]
    },
    "models": {
        "default": "openai/gpt-4.1-mini",
        "fallbacks": [
            "openai/gpt-4.1",
            "anthropic/claude-sonnet-4.5",
            "meta-llama/llama-3.3-70b-instruct"
        ],
        "defaultContextWindow": 131072,
        "defaultMaxOutputTokens": 16384,
        "catalog": {
            "openai/gpt-4.1-mini": {
                "contextWindow": 1047576,
                "maxOutputTokens": 32768,
                "pricingPerMTok": {
                    "input": 0.4,
                    "output": 1.6
                },
                "vision": true,
                "status": "production",
                "description": "Recommended default. Prime Intellect's own Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) lists this model as \"Fast, cost-effective (default)\" and uses it as the default model of its inference-backed evaluation command. No Prime-trained model appears on this roster (119 of 125 entries are gateway-routed and the other 6 are third-party models served on Prime infrastructure), so this is the model its docs designate as the default, not a Prime-trained flagship. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,047,576, max_output_tokens 32,768, $0.4/$1.6 per MTok input/output; input modalities image/text/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
            },
            "openai/gpt-4.1": {
                "contextWindow": 1047576,
                "maxOutputTokens": 32768,
                "pricingPerMTok": {
                    "input": 2,
                    "output": 8
                },
                "vision": true,
                "status": "production",
                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Higher quality\" than the default. Fallback. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,047,576, max_output_tokens 32,768, $2/$8 per MTok input/output; input modalities image/text/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
            },
            "anthropic/claude-sonnet-4.5": {
                "contextWindow": 1000000,
                "maxOutputTokens": 64000,
                "pricingPerMTok": {
                    "input": 3,
                    "output": 15
                },
                "vision": true,
                "status": "production",
                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Strong reasoning\". Fallback. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,000,000, max_output_tokens 64,000, $3/$15 per MTok input/output; input modalities text/image/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
            },
            "meta-llama/llama-3.3-70b-instruct": {
                "contextWindow": 131072,
                "maxOutputTokens": 16384,
                "pricingPerMTok": {
                    "input": 1.04,
                    "output": 2.253
                },
                "vision": false,
                "status": "production",
                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Open-weight, balanced\". Fallback. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 131,072, max_output_tokens 16,384, $1.04/$2.253 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
            },
            "google/gemini-2.5-flash": {
                "contextWindow": 1048576,
                "maxOutputTokens": 65535,
                "pricingPerMTok": {
                    "input": 0.3,
                    "output": 2.5
                },
                "vision": true,
                "status": "production",
                "description": "Listed in the Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) as \"Fast multimodal\". Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,048,576, max_output_tokens 65,535, $0.3/$2.5 per MTok input/output; input modalities file/image/text/audio/video; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
            },
            "Qwen/Qwen3-235B-A22B-Instruct-2507": {
                "contextWindow": 262144,
                "maxOutputTokens": 235929,
                "pricingPerMTok": {
                    "input": 0.25,
                    "output": 1
                },
                "vision": false,
                "status": "production",
                "description": "The Evaluating Environments guide (docs.primeintellect.ai/tutorials-environments/evaluating) lists a lowercase id, qwen/qwen3-235b-a22b-instruct-2507, as \"Large MoE model\"; that lowercase id is not on today's roster, so the id here is copied character for character from the roster's differently cased entry. The roster's max_output_tokens figure is reported as served. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 262,144, max_output_tokens 235,929, $0.25/$1 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
            },
            "z-ai/glm-5.3": {
                "contextWindow": 1048576,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 1.4,
                    "output": 4.4,
                    "cachedInput": 0.26
                },
                "vision": false,
                "status": "production",
                "description": "Serving \"hosted\" on today's roster — the vendor's OpenAPI spec (https://api.pinference.ai/openapi.json) defines that value as models served on Prime infrastructure. Roster display_name \"GLM 5.3\"; reasoning is marked mandatory with default effort \"max\". Its supported_parameters list tools and tool_choice but not response_format or structured_outputs. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,048,576, max_output_tokens 131,072, $1.4/$4.4 per MTok input/output ($0.26 cached-input read); input modalities text; supported_parameters include tools, tool_choice; serving hosted. No image input modality on the roster, so vision is false."
            },
            "openai/gpt-5.4-mini": {
                "contextWindow": 400000,
                "maxOutputTokens": 128000,
                "pricingPerMTok": {
                    "input": 0.75,
                    "output": 4.5
                },
                "vision": true,
                "status": "production",
                "description": "Named in the Troubleshooting page's direct-API examples (docs.primeintellect.ai/inference/troubleshooting). Roster reasoning efforts: xhigh/high/medium/low/none, not mandatory. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 400,000, max_output_tokens 128,000, $0.75/$4.5 per MTok input/output; input modalities file/image/text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
            },
            "openai/gpt-oss-120b": {
                "contextWindow": 131072,
                "maxOutputTokens": 65536,
                "pricingPerMTok": {
                    "input": 0.35,
                    "output": 0.75
                },
                "vision": false,
                "status": "production",
                "description": "Roster-listed only. Reasoning is marked mandatory (default effort \"medium\"). Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 131,072, max_output_tokens 65,536, $0.35/$0.75 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
            },
            "deepseek/deepseek-v4-flash": {
                "contextWindow": 1048576,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 0.44,
                    "output": 1.32
                },
                "vision": false,
                "status": "production",
                "description": "Roster-listed only. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 1,048,576, max_output_tokens 131,072, $0.44/$1.32 per MTok input/output; input modalities text; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. No image input modality on the roster, so vision is false."
            },
            "anthropic/claude-haiku-4.5": {
                "contextWindow": 200000,
                "maxOutputTokens": 64000,
                "pricingPerMTok": {
                    "input": 1,
                    "output": 5
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed only. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): context_window 200,000, max_output_tokens 64,000, $1/$5 per MTok input/output; input modalities text/image/file; supported_parameters include response_format, structured_outputs, tool_choice, tools; serving gateway. vision: true follows the roster's image input modality (no image request was sent)."
            },
            "Qwen/Qwen3.5-122B-A10B": {
                "pricingPerMTok": {
                    "input": 0.3,
                    "output": 0.9,
                    "cachedInput": 0.27
                },
                "vision": false,
                "status": "production",
                "description": "Serving \"hosted\" (Prime infrastructure) on today's roster. The roster gives it no context_window, max_output_tokens, modalities or supported_parameters, so none are declared here; vision false is the schema's required default, not a vendor statement about image input. Roster-listed only. Figures from the unauthenticated GET https://api.pinference.ai/api/v1/models roster (2026-09-29): $0.3/$0.9 per MTok input/output ($0.27 cached-input read); serving hosted."
            }
        },
        "topModels": [
            "openai/gpt-4.1-mini",
            "openai/gpt-4.1",
            "anthropic/claude-sonnet-4.5",
            "meta-llama/llama-3.3-70b-instruct",
            "google/gemini-2.5-flash",
            "Qwen/Qwen3-235B-A22B-Instruct-2507",
            "z-ai/glm-5.3",
            "openai/gpt-5.4-mini",
            "openai/gpt-oss-120b",
            "deepseek/deepseek-v4-flash",
            "anthropic/claude-haiku-4.5",
            "Qwen/Qwen3.5-122B-A10B"
        ]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": "model-dependent",
        "toolsWithStreaming": false,
        "structuredOutput": true,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [
        {
            "status": 401,
            "pattern": "Authorization header or x-api-key missing|invalid_api_key|Invalid API key",
            "class": "authentication",
            "message": "Invalid or missing Prime Intellect API key. Check {apiKeyEnvVar}. Create a key with the Inference permission enabled at {setupUrl}"
        }
    ],
    "setup": {
        "url": "https://app.primeintellect.ai/dashboard/tokens",
        "apiKeyFormat": null,
        "billingPolicy": "no-free-tier",
        "instructions": [
            "1. Visit: https://app.primeintellect.ai/dashboard/tokens (Settings -> API Keys) and sign in",
            "2. Click Generate New Key and enable the Inference permission — without it requests fail with authentication errors (https://docs.primeintellect.ai/inference/overview); the key is shown only once, so copy it straight away (https://docs.primeintellect.ai/api-reference/api-keys)",
            "3. Billing is automatic deduction from your Prime Intellect account balance (https://docs.primeintellect.ai/inference/overview); no free tier or trial credit is documented on the pages read, so add funds at https://app.primeintellect.ai/dashboard/billing and confirm current terms before the first call",
            "4. Set {apiKeyEnvVar} in your .env file (PRIME_API_KEY, the variable Prime's own docs use, is also read)"
        ],
        "description": "OpenAI-compatible endpoint at https://api.pinference.ai/api/v1 (docs.primeintellect.ai/inference/overview), a gateway that routes to upstream model providers plus a few models served on Prime infrastructure. The inference host (pinference.ai) differs from the docs and dashboard host (primeintellect.ai); both are confirmed on the vendor's own pages. The catalog schema has no 'unknown' billing value, so no-free-tier here means no free tier is documented, not that the vendor confirmed there is none."
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-29",
            "method": "unauthenticated GET https://api.pinference.ai/api/v1/models — 125 models; credential-free, no key used",
            "status": 200
        },
        "authProbe": {
            "date": "2026-09-29",
            "method": "unauthenticated GET https://api.pinference.ai/api/v1/models/openai/gpt-4.1-mini with no credentials — 401 {\"detail\":\"Authorization header or x-api-key missing\", ...}; only the missing-credential shape was observed, the invalid-key shape (error.code invalid_api_key) is from docs.primeintellect.ai/api-reference/inference-models and was not probed; credential-free, no key used",
            "status": 401
        },
        "billingProbe": {
            "date": "2026-09-29",
            "method": "public page https://docs.primeintellect.ai/inference/overview — \"Automatic deduction from your Prime Intellect account balance\"; https://docs.primeintellect.ai/inference/troubleshooting documents an insufficient_funds error; no free tier stated; credential-free"
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
    }
}