InferX — kaged models

id: inferx

npm: @ai-sdk/openai-compatible

env: INFERX_API_KEY

api: https://model.inferx.net/endpoints/v1

doc: https://model.inferx.net/endpoints

Models

Agents-A1

in $0.00/M

out $0.00/M

ctx: 262,000 max out: 100,000 in: text, image out: text

reasoning tools vision structured temp open weights

deepseek-v4-flash

in $0.00/M

out $0.00/M

ctx: 1,000,000 max out: 100,000 in: text out: text

reasoning tools vision structured temp open weights

Devstral-2-123B-Instruct-2512-int4-AutoRound

in $0.00/M

out $0.00/M

ctx: 128,000 max out: 128,000 in: text out: text

reasoning tools vision structured temp open weights

Gemma 4 31B IT FP8

gemma-4-31B-it-fp8

in $0.00/M

out $0.00/M

ctx: 262,144 max out: 32,768 in: text, image out: text

reasoning tools vision structured temp open weights

mimo-v25

in $0.00/M

out $0.00/M

ctx: 1,000,000 max out: 100,000 in: text, image, audio, video out: text

reasoning tools vision structured temp open weights

Ornith-1.0-35B-FP8

in $0.00/M

out $0.00/M

ctx: 262,000 max out: 100,000 in: text, image out: text

reasoning tools vision structured temp open weights

Qwen3 Coder Next FP8

Qwen3-Coder-Next-FP8

in $0.00/M

out $0.00/M

ctx: 256,144 max out: 65,536 in: text out: text

reasoning tools vision structured temp open weights

Qwen3-Coder-Next-FP8-no-thinking

in $0.00/M

out $0.00/M

ctx: 260,000 max out: 65,536 in: text out: text

reasoning tools vision structured temp open weights

Qwen3-Embedding-8B

in $0.00/M

out $0.00/M

ctx: 32,768 max out: 0 in: text out: text

reasoning tools vision structured temp open weights

Qwen3.6 27B FP8

Qwen3.6-27B-FP8

in $0.00/M

out $0.00/M

ctx: 262,144 max out: 65,536 in: text, image, video, audio out: text

reasoning tools vision structured temp open weights

Qwen3.6 35B A3B FP8

Qwen3.6-35B-A3B-FP8

in $0.00/M

out $0.00/M

ctx: 262,000 max out: 65,536 in: text, image, video, audio out: text

reasoning tools vision structured temp open weights

Qwen3.6-35B-A3B-fp8-no-thinking

in $0.00/M

out $0.00/M

ctx: 262,000 max out: 65,536 in: text, image, video, audio out: text

reasoning tools vision structured temp open weights