{
    "$schema": "./provider-catalog.schema.json",
    "id": "above-dev",
    "displayName": "above.dev",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.above.dev/v1"
    },
    "models": {
        "default": "deepseek-v4.1-flash",
        "fallbacks": [
            "glm-5.3-flash",
            "mimo-v2.6-flash",
            "deepseek-v4-pro",
            "glm-5.2",
            "mimo-v2.6-pro",
            "glm-5.2-fast",
            "qwen3.8-max",
            "mimo-v2.6-pro-ultraspeed"
        ],
        "defaultContextWindow": 1000000,
        "defaultMaxOutputTokens": 131072,
        "catalog": {
            "deepseek-v4.1-flash": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "vision": true,
                "status": "production",
                "description": "DeepSeek V4.1 Flash (also addressable as deepseek-v4-flash), tier T1. above.dev's own default: naming no model routes here (\"the cheapest model in the catalog\", https://above.dev/docs, retrieved 2026-09-28). GET /v1/models (unauthenticated, 2026-09-28) self-reports supports_tool_calls, supports_streaming, supports_json_mode, supports_structured_output and supports_vision all true, and supports_reasoning true, but none of this was independently probed — no key was used. Pricing uses above.dev's documented time-of-day split (peak 01:00-04:00 and 06:00-10:00 UTC weekdays, else off-peak; weekends fully off-peak in Beijing time) so pricingPerMTok is omitted rather than collapsed to one number: input $0.165-$0.33/M, cache-hit $0.0033-$0.0066/M, output $0.66-$1.32/M (https://above.dev/docs, retrieved 2026-09-28)."
            },
            "deepseek-v4-pro": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "vision": false,
                "status": "production",
                "description": "DeepSeek V4 Pro, tier T2 (\"Agentic — multi-step, tool-capable\" per the docs' tier table). Roster-listed via unauthenticated GET /v1/models (2026-09-28); not capability-probed. Time-of-day pricing per https://above.dev/docs (retrieved 2026-09-28) — input $0.726-$1.452/M, cache-hit $0.0242-$0.0484/M, output $2.178-$4.356/M — so pricingPerMTok is omitted (see deepseek-v4.1-flash for why)."
            },
            "glm-5.2": {
                "contextWindow": 1048576,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 1.54,
                    "output": 4.84,
                    "cachedInput": 0.154
                },
                "vision": false,
                "status": "production",
                "description": "Zhipu GLM 5.2, tier T2. Roster-listed via unauthenticated GET /v1/models (2026-09-28); not capability-probed. Flat (non-time-of-day) pricing per https://above.dev/docs, retrieved 2026-09-28."
            },
            "glm-5.3-flash": {
                "contextWindow": 1048576,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 0.165,
                    "output": 0.55,
                    "cachedInput": 0.0319
                },
                "vision": true,
                "status": "production",
                "description": "Zhipu GLM 5.3 Flash, tier T1. Roster-listed via unauthenticated GET /v1/models (2026-09-28), which self-reports supports_vision true for this id; not capability-probed with a real image. Flat pricing per https://above.dev/docs, retrieved 2026-09-28. Note: a separate id, glm-5.3-flash-modal, is named in the docs' Limits section as one of two \"free-tier routes\" capped at 16,384 output tokens — that id does not appear in the current /v1/models roster and is a distinct route from this one; not represented in this catalog."
            },
            "glm-5.2-fast": {
                "contextWindow": 1048576,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 2.31,
                    "output": 7.26,
                    "cachedInput": 0.231
                },
                "vision": false,
                "status": "production",
                "description": "Zhipu GLM 5.2 Fast, tier T3 (\"Highest capability in the catalog\" per the docs' tier table). Roster-listed via unauthenticated GET /v1/models (2026-09-28); not capability-probed. Flat pricing per https://above.dev/docs, retrieved 2026-09-28."
            },
            "qwen3.8-max": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 2.2,
                    "output": 6.6,
                    "cachedInput": 0.275
                },
                "vision": true,
                "status": "production",
                "description": "Alibaba Qwen 3.8 Max, tier T3. Roster-listed via unauthenticated GET /v1/models (2026-09-28), which self-reports supports_vision true for this id; not capability-probed with a real image. Flat pricing per https://above.dev/docs, retrieved 2026-09-28."
            },
            "mimo-v2.6-pro": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 0.5077,
                    "output": 1.0154,
                    "cachedInput": 0.0042
                },
                "vision": false,
                "status": "production",
                "description": "MiMo V2.6 Pro (also addressable as mimo-v2.5-pro), tier T2. Roster-listed via unauthenticated GET /v1/models (2026-09-28); not capability-probed. Flat pricing per https://above.dev/docs, retrieved 2026-09-28."
            },
            "mimo-v2.6-flash": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 0.1692,
                    "output": 0.3385,
                    "cachedInput": 0.0034
                },
                "vision": false,
                "status": "production",
                "description": "MiMo V2.6 Flash, tier T1. Roster-listed via unauthenticated GET /v1/models (2026-09-28); not capability-probed. Flat pricing per https://above.dev/docs, retrieved 2026-09-28."
            },
            "mimo-v2.6-pro-ultraspeed": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 5.0769,
                    "output": 10.1538,
                    "cachedInput": 0.0423
                },
                "vision": false,
                "status": "production",
                "description": "MiMo V2.6 Pro UltraSpeed, tier T3. Roster-listed via unauthenticated GET /v1/models (2026-09-28); not capability-probed. Flat pricing per https://above.dev/docs, retrieved 2026-09-28."
            }
        },
        "topModels": [
            "deepseek-v4.1-flash",
            "glm-5.3-flash",
            "mimo-v2.6-flash",
            "deepseek-v4-pro",
            "glm-5.2",
            "mimo-v2.6-pro",
            "glm-5.2-fast",
            "qwen3.8-max",
            "mimo-v2.6-pro-ultraspeed"
        ]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": "model-dependent",
        "toolsWithStreaming": false,
        "structuredOutput": false,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [
        {
            "status": 401,
            "class": "authentication",
            "message": "Invalid or missing above.dev API key (401 Unauthorised). Check {apiKeyEnvVar}. Get one at {setupUrl}"
        },
        {
            "status": 402,
            "class": "provider",
            "message": "above.dev account balance is insufficient (402 payment required). Top up at https://above.dev/pricing"
        },
        {
            "status": 403,
            "class": "invalid-model",
            "message": "above.dev model '{model}' is not enabled for this key (403 model_not_allowed_for_key) — it may be plan-restricted or in private beta. Pick another model or contact above.dev."
        },
        {
            "status": 429,
            "class": "rate-limit",
            "message": "above.dev rate limit exceeded (429 rate_limit_exceeded, 300 requests/minute per account). Retry after the documented Retry-After header."
        },
        {
            "status": 504,
            "class": "network",
            "message": "above.dev upstream model did not respond in time (504 provider_timeout). Retry the request."
        }
    ],
    "setup": {
        "url": "https://above.dev/pricing",
        "apiKeyFormat": "^sk-gw-.+$",
        "billingPolicy": "no-free-tier",
        "instructions": [
            "1. Visit: https://above.dev/pricing and purchase credit — API keys are issued only after purchase, there is no free signup",
            "2. Copy the issued key — it starts with sk-gw- (the docs give only the prefix, not a full character-set spec)",
            "3. Manage or rotate the key from https://above.dev/dashboard if it is ever compromised — a key grants full access to your credit balance",
            "4. Set {apiKeyEnvVar} in your .env file"
        ],
        "description": "OpenAI-compatible gateway at https://api.above.dev/v1, routing to a small DeepSeek/GLM/Qwen/MiMo catalog. POST /v1/chat/completions is documented as an alias that delegates to the vendor's native POST /v1/messages with \"identical behaviour\". No free tier for account access — a key is issued only after purchase at above.dev/pricing (the docs separately mention two lower-cap \"free-tier routes\", glm-5.3-flash-modal and deepseek-v4.1-flash-modal, but those ids are outside the current /v1/models roster and still require a purchased key). Account-wide rate limit is 300 requests/minute; every current model accepts up to 131,072 output tokens. The docs describe the `tools` and `response_format` request fields only as routing signals (\"presence influences routing toward tool-capable models\" / \"scores toward structured-output models\"), in explicit contrast to `tool_choice` and `temperature`, which the same table states are \"passed through to the model\" — so this entry does not assert tool calling or structured output as a confirmed, working capability without a live probe."
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-28",
            "method": "unauthenticated GET https://api.above.dev/v1/models — 9 models; credential-free, no key used",
            "status": 200
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1848"
    }
}