Add InferX provider (OpenAI-compatible endpoints)

providers/inferx/models/google/gemma-4-31b-it-fp8.toml

@@ -0,0 +1,21 @@
+name = "Gemma 4 31B IT FP8"
+family = "gemma"
+release_date = "2026-05"
+last_updated = "2026-05-05"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 262144
+output = 8192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/inferx/models/qwen/qwen3-coder-next-fp8-1m.toml

@@ -0,0 +1,21 @@
+name = "Qwen3 Coder Next FP8 1M"
+family = "qwen"
+release_date = "2026-05"
+last_updated = "2026-05-12"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 1024000
+output = 8192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/inferx/models/qwen/qwen3-coder-next-fp8.toml

@@ -0,0 +1,21 @@
+name = "Qwen3 Coder Next FP8"
+family = "qwen"
+release_date = "2026-05"
+last_updated = "2026-05-08"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 256144
+output = 8192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/inferx/models/qwen/qwen3.5-122b-a10b-nvfp4.toml

@@ -0,0 +1,21 @@
+name = "Qwen3.5 122B A10B NVFP4"
+family = "qwen3.5"
+release_date = "2026-05"
+last_updated = "2026-05-13"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 256144
+output = 8192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/inferx/models/qwen/qwen3.6-27b-fp8.toml

@@ -0,0 +1,21 @@
+name = "Qwen3.6 27B FP8"
+family = "qwen3.6"
+release_date = "2026-05"
+last_updated = "2026-05-13"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 262144
+output = 8192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/inferx/models/qwen/qwen3.6-35b-a3b-fp8.toml

@@ -0,0 +1,21 @@
+name = "Qwen3.6 35B A3B FP8"
+family = "qwen3.6"
+release_date = "2026-05"
+last_updated = "2026-05-13"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 262000
+output = 8192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/inferx/provider.toml

@@ -0,0 +1,5 @@
+name = "InferX"
+env = ["INFERX_API_KEY"]
+npm = "@ai-sdk/openai-compatible"
+api = "https://model.inferx.net/v1"
+doc = "https://inferx.net"