Skip to content

Commit a9e2782

Browse files
HuggingFaceInfraWauplin
HuggingFaceInfra
and
Wauplin
authored
Update Inference Providers documentation (automated) (#2638)
Co-authored-by: Wauplin <11801849+Wauplin@users.noreply.github.com>
1 parent cf4c525 commit a9e2782

11 files changed

Lines changed: 30 additions & 23 deletions

File tree

‎docs/inference-providers/providers/fireworks-ai.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
4646

4747
<InferenceSnippet
4848
pipeline=text-generation
49-
providersMapping={ {"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"accounts/fireworks/models/deepseek-v4-pro"} } }
49+
providersMapping={ {"fireworks-ai":{"modelId":"zai-org/GLM-5.2","providerModelId":"accounts/fireworks/models/glm-5p2"} } }
5050
conversational />
5151

5252

‎docs/inference-providers/providers/hf-inference.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,7 @@ Find out more about Automatic Speech Recognition [here](../tasks/automatic-speec
5050

5151
<InferenceSnippet
5252
pipeline=automatic-speech-recognition
53-
providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper-large-v3"} } }
53+
providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3-turbo","providerModelId":"openai/whisper-large-v3-turbo"} } }
5454
/>
5555

5656

@@ -60,7 +60,7 @@ Find out more about Feature Extraction [here](../tasks/feature-extraction).
6060

6161
<InferenceSnippet
6262
pipeline=feature-extraction
63-
providersMapping={ {"hf-inference":{"modelId":"BAAI/bge-small-en-v1.5","providerModelId":"BAAI/bge-small-en-v1.5"} } }
63+
providersMapping={ {"hf-inference":{"modelId":"microsoft/harrier-oss-v1-0.6b","providerModelId":"microsoft/harrier-oss-v1-0.6b"} } }
6464
/>
6565

6666

‎docs/inference-providers/providers/together.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -57,7 +57,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
5757

5858
<InferenceSnippet
5959
pipeline=text-generation
60-
providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"} } }
60+
providersMapping={ {"together":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/GLM-5.2"} } }
6161
conversational />
6262

6363

‎docs/inference-providers/providers/zai-org.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -66,7 +66,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
6666

6767
<InferenceSnippet
6868
pipeline=image-text-to-text
69-
providersMapping={ {"zai-org":{"modelId":"zai-org/GLM-4.5V","providerModelId":"glm-4.5v"} } }
69+
providersMapping={ {"zai-org":{"modelId":"zai-org/GLM-4.6V","providerModelId":"glm-4.6v"} } }
7070
conversational />
7171

7272

‎docs/inference-providers/tasks/automatic-speech-recognition.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ Explore all available models and find the one that suits you best [here](https:/
3636

3737
<InferenceSnippet
3838
pipeline=automatic-speech-recognition
39-
providersMapping={ {"deepinfra":{"modelId":"nvidia/nemotron-3.5-asr-streaming-0.6b","providerModelId":"nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b"},"fal-ai":{"modelId":"nvidia/nemotron-3.5-asr-streaming-0.6b","providerModelId":"nvidia/nemotron-asr-multilingual/asr"},"hf-inference":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper-large-v3"},"replicate":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper:8099696689d249cf8b122d833c36ac3f75505c666a395ca40ef26f68e7d3d16e"},"together":{"modelId":"nvidia/nemotron-3.5-asr-streaming-0.6b","providerModelId":"nvidia/nemotron-3.5-asr-streaming-0.6b"}} }
39+
providersMapping={ {"deepinfra":{"modelId":"nvidia/nemotron-3.5-asr-streaming-0.6b","providerModelId":"nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b"},"fal-ai":{"modelId":"nvidia/nemotron-3.5-asr-streaming-0.6b","providerModelId":"nvidia/nemotron-asr-multilingual/asr"},"hf-inference":{"modelId":"openai/whisper-large-v3-turbo","providerModelId":"openai/whisper-large-v3-turbo"},"replicate":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper:8099696689d249cf8b122d833c36ac3f75505c666a395ca40ef26f68e7d3d16e"},"together":{"modelId":"nvidia/nemotron-3.5-asr-streaming-0.6b","providerModelId":"nvidia/nemotron-3.5-asr-streaming-0.6b"}} }
4040
/>
4141

4242

‎docs/inference-providers/tasks/chat-completion.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ The API supports:
6464

6565
<InferenceSnippet
6666
pipeline=text-generation
67-
providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/tiny-aya-global","providerModelId":"tiny-aya-global"},"deepinfra":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/GLM-5.2"},"featherless-ai":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/GLM-5.2"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"accounts/fireworks/models/deepseek-v4-pro"},"groq":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"},"novita":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/glm-5.2"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"ovhcloud":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"},"scaleway":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"llama-3.1-8b-instruct"},"together":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"zai-org":{"modelId":"zai-org/GLM-5.2","providerModelId":"glm-5.2"}} }
67+
providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/tiny-aya-global","providerModelId":"tiny-aya-global"},"deepinfra":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/GLM-5.2"},"featherless-ai":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/GLM-5.2"},"fireworks-ai":{"modelId":"zai-org/GLM-5.2","providerModelId":"accounts/fireworks/models/glm-5p2"},"groq":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"},"novita":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/glm-5.2"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"ovhcloud":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"},"scaleway":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"llama-3.1-8b-instruct"},"together":{"modelId":"zai-org/GLM-5.2","providerModelId":"zai-org/GLM-5.2"},"zai-org":{"modelId":"zai-org/GLM-5.2","providerModelId":"glm-5.2"}} }
6868
conversational />
6969

7070

@@ -74,7 +74,7 @@ conversational />
7474

7575
<InferenceSnippet
7676
pipeline=image-text-to-text
77-
providersMapping={ {"cerebras":{"modelId":"google/gemma-4-31B-it","providerModelId":"gemma-4-31b"},"cohere":{"modelId":"CohereLabs/aya-vision-32b","providerModelId":"c4ai-aya-vision-32b"},"deepinfra":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"featherless-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"fireworks-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"accounts/fireworks/models/minimax-m3"},"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"novita":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"minimax/minimax-m3"},"nscale":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"},"ovhcloud":{"modelId":"Qwen/Qwen3.6-27B","providerModelId":"Qwen3.6-27B"},"scaleway":{"modelId":"Qwen/Qwen3.5-397B-A17B","providerModelId":"qwen3.5-397b-a17b"},"together":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"zai-org":{"modelId":"zai-org/GLM-4.5V","providerModelId":"glm-4.5v"}} }
77+
providersMapping={ {"cerebras":{"modelId":"google/gemma-4-31B-it","providerModelId":"gemma-4-31b"},"cohere":{"modelId":"CohereLabs/aya-vision-32b","providerModelId":"c4ai-aya-vision-32b"},"deepinfra":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"featherless-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"fireworks-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"accounts/fireworks/models/minimax-m3"},"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"novita":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"minimax/minimax-m3"},"nscale":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"},"ovhcloud":{"modelId":"Qwen/Qwen3.6-27B","providerModelId":"Qwen3.6-27B"},"scaleway":{"modelId":"Qwen/Qwen3.5-397B-A17B","providerModelId":"qwen3.5-397b-a17b"},"together":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"zai-org":{"modelId":"zai-org/GLM-4.6V","providerModelId":"glm-4.6v"}} }
7878
conversational />
7979

8080

‎docs/inference-providers/tasks/feature-extraction.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ Explore all available models and find the one that suits you best [here](https:/
3636

3737
<InferenceSnippet
3838
pipeline=feature-extraction
39-
providersMapping={ {"hf-inference":{"modelId":"BAAI/bge-small-en-v1.5","providerModelId":"BAAI/bge-small-en-v1.5"},"scaleway":{"modelId":"Qwen/Qwen3-Embedding-8B","providerModelId":"qwen3-embedding-8b"},"together":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"}} }
39+
providersMapping={ {"hf-inference":{"modelId":"microsoft/harrier-oss-v1-0.6b","providerModelId":"microsoft/harrier-oss-v1-0.6b"},"scaleway":{"modelId":"Qwen/Qwen3-Embedding-8B","providerModelId":"qwen3-embedding-8b"},"together":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"}} }
4040
/>
4141

4242

‎docs/inference-providers/tasks/image-text-to-text.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ Explore all available models and find the one that suits you best [here](https:/
3131

3232
<InferenceSnippet
3333
pipeline=image-text-to-text
34-
providersMapping={ {"cerebras":{"modelId":"google/gemma-4-31B-it","providerModelId":"gemma-4-31b"},"cohere":{"modelId":"CohereLabs/aya-vision-32b","providerModelId":"c4ai-aya-vision-32b"},"deepinfra":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"featherless-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"fireworks-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"accounts/fireworks/models/minimax-m3"},"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"novita":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"minimax/minimax-m3"},"nscale":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"},"ovhcloud":{"modelId":"Qwen/Qwen3.6-27B","providerModelId":"Qwen3.6-27B"},"scaleway":{"modelId":"Qwen/Qwen3.5-397B-A17B","providerModelId":"qwen3.5-397b-a17b"},"together":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"zai-org":{"modelId":"zai-org/GLM-4.5V","providerModelId":"glm-4.5v"}} }
34+
providersMapping={ {"cerebras":{"modelId":"google/gemma-4-31B-it","providerModelId":"gemma-4-31b"},"cohere":{"modelId":"CohereLabs/aya-vision-32b","providerModelId":"c4ai-aya-vision-32b"},"deepinfra":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"featherless-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"fireworks-ai":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"accounts/fireworks/models/minimax-m3"},"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"novita":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"minimax/minimax-m3"},"nscale":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"},"ovhcloud":{"modelId":"Qwen/Qwen3.6-27B","providerModelId":"Qwen3.6-27B"},"scaleway":{"modelId":"Qwen/Qwen3.5-397B-A17B","providerModelId":"qwen3.5-397b-a17b"},"together":{"modelId":"MiniMaxAI/MiniMax-M3","providerModelId":"MiniMaxAI/MiniMax-M3"},"zai-org":{"modelId":"zai-org/GLM-4.6V","providerModelId":"glm-4.6v"}} }
3535
conversational />
3636

3737

‎docs/inference-providers/tasks/token-classification.md‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -65,5 +65,12 @@ Explore all available models and find the one that suits you best [here](https:/
6565

6666
| Body | |
6767
| :--- | :--- | :--- |
68+
| **(array)** | _object[]_ | Output is an array of objects. |
69+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;entity_group** | _string_ | The predicted label for a group of one or more tokens |
70+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;entity** | _string_ | The predicted label for a single token |
71+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_ | The associated score / probability |
72+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;word** | _string_ | The corresponding text |
73+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;start** | _integer_ | The character position in the input where this group begins. |
74+
| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;end** | _integer_ | The character position in the input where this group ends. |
6875

6976

‎scripts/inference-providers/package.json‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -14,8 +14,8 @@
1414
"author": "",
1515
"license": "ISC",
1616
"dependencies": {
17-
"@huggingface/inference": "^4.13.22",
18-
"@huggingface/tasks": "^0.21.22",
17+
"@huggingface/inference": "^4.13.23",
18+
"@huggingface/tasks": "^0.21.25",
1919
"@types/node": "^22.5.0",
2020
"handlebars": "^4.7.8",
2121
"node": "^20.17.0",

0 commit comments

Comments
 (0)