{"record":{"id":"a4ac2c57563db19e","repo":"BerriAI/litellm","slug":"unmapped-model-received-expected","errorCode":null,"errorMessage":"Unmapped model. Received={}. Expected={}","messagePattern":"Unmapped model\\. Received=(.+?)\\. Expected=(.+?)","errorType":"exception","errorClass":"Exception","httpStatus":null,"severity":"error","filePath":"litellm/llms/bedrock/embed/embedding.py","lineNumber":440,"sourceCode":"                    transformed_request: AmazonEmbeddingRequest = (\n                        AmazonTitanMultimodalEmbeddingG1Config()._transform_request(\n                            input=i, inference_params=inference_params\n                        )\n                    )\n                elif model == \"amazon.titan-embed-text-v1\":\n                    transformed_request = AmazonTitanG1Config()._transform_request(\n                        input=i, inference_params=inference_params\n                    )\n                elif model == \"amazon.titan-embed-text-v2:0\":\n                    transformed_request = AmazonTitanV2Config()._transform_request(\n                        input=i, inference_params=inference_params\n                    )\n                elif model == \"amazon.titan-embed-g1-text-02\":\n                    transformed_request = AmazonTitanG1Config()._transform_request(\n                        input=i, inference_params=inference_params\n                    )\n                else:\n                    raise Exception(\n                        \"Unmapped model. Received={}. Expected={}\".format(\n                            model,\n                            [\n                                \"amazon.titan-embed-image-v1\",\n                                \"amazon.titan-embed-text-v1\",\n                                \"amazon.titan-embed-text-v2:0\",\n                                \"amazon.titan-embed-g1-text-02\",\n                            ],\n                        )\n                    )\n                batch_data.append(transformed_request)\n        elif provider == \"twelvelabs\":\n            batch_data = []\n            for i in input:\n                twelvelabs_request = TwelveLabsMarengoEmbeddingConfig()._transform_request(\n                    input=i,\n                    inference_params=inference_params,\n                    async_invoke_route=has_async_invoke,","sourceCodeStart":422,"sourceCodeEnd":458,"githubUrl":"https://github.com/BerriAI/litellm/blob/6c2dcb801bf2b75c18f1bb24140e7cf57465cc4d/litellm/llms/bedrock/embed/embedding.py#L422-L458","documentation":"Inside the amazon/titan batch loop, the model string did not equal any of the four hard-coded titan ids (amazon.titan-embed-image-v1, amazon.titan-embed-text-v1, amazon.titan-embed-text-v2:0, amazon.titan-embed-g1-text-02), so no request transformer could be chosen. Note the message template uses {} placeholders — it renders literally instead of interpolating, which is a minor logging bug in the source.","triggerScenarios":"Provider inference routed to the amazon family (model contains 'titan'/'amazon') but the exact id differs — e.g. 'amazon.titan-embed-text-v2:0 ' with whitespace, wrong casing, a regional suffix, or a new titan variant not in the list.","commonSituations":"Copy-pasting model ids with trailing whitespace or unicode quotes; newly launched titan embedding versions on an older litellm; case-mismatched ids.","solutions":["Use one of the four exact ids listed in the error: amazon.titan-embed-image-v1, amazon.titan-embed-text-v1, amazon.titan-embed-text-v2:0, amazon.titan-embed-g1-text-02.","Strip/normalize the model string (whitespace, case) before calling.","Upgrade litellm if AWS shipped a new titan embedding model."],"exampleFix":"# before\nresp = litellm.embedding(model=\"bedrock/amazon.titan-embed-text-v1 \", input=[\"hi\"])\n\n# after\nresp = litellm.embedding(model=\"bedrock/amazon.titan-embed-text-v2:0\", input=[\"hi\"])","handlingStrategy":"validation","validationCode":"TITAN_MODELS = {\"amazon.titan-embed-image-v1\", \"amazon.titan-embed-text-v1\", \"amazon.titan-embed-text-v2:0\", \"amazon.titan-embed-g1-text-02\"}\nassert model.strip() in TITAN_MODELS, f\"unsupported titan id: {model!r}\"","typeGuard":"def is_known_titan_id(model: str) -> bool:\n    return model.strip() in {\n        \"amazon.titan-embed-image-v1\",\n        \"amazon.titan-embed-text-v1\",\n        \"amazon.titan-embed-text-v2:0\",\n        \"amazon.titan-embed-g1-text-02\",\n    }","tryCatchPattern":null,"preventionTips":["Load model ids from config rather than typing them inline.","Strip whitespace/case-normalize ids at the request boundary.","Watch litellm release notes when AWS ships new titan variants."],"tags":["bedrock","titan","embedding","model-id"],"backgroundTag":null,"analyzedSha":"6c2dcb801bf2b75c18f1bb24140e7cf57465cc4d","analyzedAt":"2026-08-15T07:12:03.035Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}