{"api":"v1","generated_at":"2026-09-16T07:19:23.734Z","licence":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"TOLL, with a link to the page cited"},"page":"https://tollindex.com/e/x402-orthogonal-com-baseten-v1-chat-completions-9d5f66","pinned_page":"https://tollindex.com/e/x402-orthogonal-com-baseten-v1-chat-completions-9d5f66/at/2026-09-16T04-48Z","pinned":false,"method":"https://tollindex.com/ledger/method","snapshot_at":"2026-09-16T04:48:25.992Z","snapshot_stamp":"2026-09-16T04-48Z","endpoint":{"slug":"x402-orthogonal-com-baseten-v1-chat-completions-9d5f66","canonical_url":"https://x402.orthogonal.com/baseten/v1/chat/completions","resource":"https://x402.orthogonal.com/baseten/v1/chat/completions","http_method":"POST","type":"http","x402_version":2,"registries":["cdp"],"primary_registry":"cdp","curated_by_coinbase":false,"description":"Send a conversation to a model and get a completion back. Works exactly like the OpenAI chat completions endpoint. Pass messages and a model slug, get a response with the assistant's reply. Supports streaming for real-time token delivery, tool calling for function execution, structured outputs via response_format, and controllable reasoning depth on supported models. | ERROR: Unable to calculate price.","service_name":null,"declared_category":null,"declared_tags":[],"route_template":null,"registry_updated":"2026-09-14T18:46:23.487Z"},"derived":{"note":"fields no registry supplies; TOLL derives them and marks them derived on the page","title":"chat completions","category":"inference","first_observed_by_toll":"2026-09-10T19:08:24.178Z","last_observed_by_toll":"2026-09-16T04:48:25.991Z","observation_began":"2026-09-10"},"presence":{"listed_now":true,"first_absent_at":null,"delisting_confirmed_at":null,"events":[{"registry":"cdp","at":"2026-09-10T19:08:24.178Z","event":"listed"}]},"accepts":[{"registry":"cdp","ordinal":0,"network":"eip155:8453","asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","asset_name":"USD Coin","symbol":"USDC","decimals":6,"amount_display":"0.005 USDC","amount_units":0.005,"decimals_known":true,"pay_to":"0xDEFaDa13F790cf39168691B391Cfa0b6f1f5c267","scheme":"exact"},{"registry":"cdp","ordinal":1,"network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","asset_name":null,"symbol":"USDC","decimals":6,"amount_display":"0.005 USDC","amount_units":0.005,"decimals_known":true,"pay_to":"6tBjD7Pyx9smaubkFaePv1NtfLh9jwLGu63MoozRmYvQ","scheme":"exact"},{"registry":"cdp","ordinal":2,"network":"eip155:143","asset":"0x754704bc059f8c67012fed69bc8a327a5aafb603","asset_name":"USDC","symbol":null,"decimals":null,"amount_display":"5000 smallest units, decimals unknown","amount_units":null,"decimals_known":false,"pay_to":"0xDEFaDa13F790cf39168691B391Cfa0b6f1f5c267","scheme":"exact"}],"counters":{"observed_at":"2026-09-16T04:48:25.992Z","calls_30d":183,"unique_payers_30d":2,"last_called_at":"2026-09-14T18:46:23.311Z"},"validation":{"latest":{"observed_at":"2026-09-16T05:43:52.350Z","state":"pass","failed_checks":["bazaar.info.output"],"endpoint_http_status":402,"run_id":"daily-2026-09-16"},"uptime":[{"days":7,"observed":6,"passed":6,"ratio":1},{"days":30,"observed":6,"passed":6,"ratio":1},{"days":90,"observed":6,"passed":6,"ratio":1}],"history_90d":[{"observed_at":"2026-09-16T05:43:52.350Z","state":"pass","failed_checks":["bazaar.info.output"],"run_id":"daily-2026-09-16","state_changed":false},{"observed_at":"2026-09-15T06:00:42.828Z","state":"pass","failed_checks":["bazaar.info.output"],"run_id":"daily-2026-09-15","state_changed":false},{"observed_at":"2026-09-14T05:32:09.128Z","state":"pass","failed_checks":["bazaar.info.output"],"run_id":"daily-2026-09-14","state_changed":false},{"observed_at":"2026-09-13T05:26:44.076Z","state":"pass","failed_checks":["bazaar.info.output"],"run_id":"daily-2026-09-13","state_changed":false},{"observed_at":"2026-09-12T07:43:27.065Z","state":"pass","failed_checks":["bazaar.info.output"],"run_id":"daily-2026-09-12","state_changed":false},{"observed_at":"2026-09-11T11:33:39.421Z","state":"pass","failed_checks":["bazaar.info.output"],"run_id":"daily-2026-09-11","state_changed":true}]},"seller":{"wallet":"0xDEFaDa13F790cf39168691B391Cfa0b6f1f5c267","page":"https://tollindex.com/seller/0xDEFaDa13F790cf39168691B391Cfa0b6f1f5c267","endpoints":1,"hosts":1},"reports":0,"registry_record":{"cdp":[{"type":"http","accepts":[{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","extra":{"name":"USD Coin","version":"2"},"payTo":"0xDEFaDa13F790cf39168691B391Cfa0b6f1f5c267","amount":"5000","scheme":"exact","network":"eip155:8453","maxTimeoutSeconds":300},{"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","extra":{"feePayer":"Hc3sdEAsCGQcpgfivywog9uwtk8gUBUZgsxdME1EJy88"},"payTo":"6tBjD7Pyx9smaubkFaePv1NtfLh9jwLGu63MoozRmYvQ","amount":"5000","scheme":"exact","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","maxTimeoutSeconds":300},{"asset":"0x754704Bc059F8C67012fEd69BC8A327a5aafb603","extra":{"name":"USDC","version":"2"},"payTo":"0xDEFaDa13F790cf39168691B391Cfa0b6f1f5c267","amount":"5000","scheme":"exact","network":"eip155:143","maxTimeoutSeconds":300}],"quality":{"lastCalledAt":"2026-09-14T18:46:23.311Z","l30DaysTotalCalls":183,"l30DaysUniquePayers":2},"resource":"https://x402.orthogonal.com/baseten/v1/chat/completions","extensions":{"bazaar":{"info":{"input":{"body":{"model":"model","messages":[]},"type":"http","method":"POST","bodyType":"json"}},"schema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","properties":{"n":{"type":"number","description":"Number of completions to generate. Currently only supports 1."},"bad":{"type":"string","description":"Words or phrases the model should avoid generating. Passed as a string."},"echo":{"type":"boolean","description":"If true, prepends the last input message to the generated output."},"seed":{"type":"number","description":"Integer for deterministic sampling. Same seed with same parameters should return the same result. Not guaranteed across model versions."},"stop":{"type":"string","description":"Up to 4 sequences where the model will stop generating. Can be a string or array of strings."},"user":{"type":"string","description":"A unique string identifying the end user. Useful for abuse monitoring and rate limiting."},"min_p":{"type":"number","description":"Minimum probability threshold. Tokens below this probability relative to the most likely token are filtered out."},"model":{"type":"string","description":"Model slug to run inference against. Available models: deepseek-ai/DeepSeek-V3-0324 (164k context, reasoning), deepseek-ai/DeepSeek-V3.1 (164k context, reasoning), zai-org/GLM-4.6 (200k context, reasoning), zai-org/GLM-4.7 (200k context, reasoning), moonshotai/Kimi-K2-Instruct-0905 (128k context), moonshotai/Kimi-K2-Thinking (262k context, always-on reasoning), moonshotai/Kimi-K2.5 (262k context), openai/gpt-oss-120b (128k context). Reasoning models support the reasoning_effort parameter for controlling thinking depth."},"tools":{"type":"array","description":"Array of tool/function definitions the model can call. Each tool has {\"type\": \"function\", \"function\": {\"name\": \"...\", \"description\": \"...\", \"parameters\": {...}}}. The model may respond with tool_calls instead of content."},"top_k":{"type":"number","description":"Top-K sampling. Only the K most likely next tokens are considered. Lower values make output more focused."},"top_p":{"type":"number","description":"Nucleus sampling threshold between 0 and 1. Only tokens within this cumulative probability mass are considered. 0.1 means only the top 10%. Use as an alternative to temperature."},"stream":{"type":"boolean","description":"If true, returns server-sent events (SSE) with partial message deltas as tokens are generated, instead of waiting for the full response."},"best_of":{"type":"number","description":"Number of candidate completions to generate server-side, returning the best. Currently only supports 1."},"logprobs":{"type":"boolean","description":"If true, returns the log probabilities of each output token in the response."},"messages":{"type":"array","description":"Array of message objects, each with a 'role' (system, user, assistant, tool) and 'content' (string or array of content parts). This is the conversation history sent to the model."},"documents":{"type":"array","description":"Array of document objects for retrieval-augmented generation (RAG). Each document has content the model can reference when responding."},"top_p_min":{"type":"number","description":"Minimum dynamic nucleus sampling threshold. Sets a floor for top_p when using adaptive sampling."},"ignore_eos":{"type":"boolean","description":"If true, the model continues generating past the end-of-sequence token."},"logit_bias":{"type":"object","description":"Map of token IDs to bias values (-100 to 100). Increase or decrease the likelihood of specific tokens appearing in the output."},"max_tokens":{"type":"number","description":"Maximum number of tokens to generate in the response. Default is 4096."},"min_tokens":{"type":"number","description":"Minimum number of tokens to generate before any stop condition can trigger."},"temperature":{"type":"number","description":"Sampling temperature between 0 and 4. Lower values (e.g. 0.2) produce more focused, deterministic output. Higher values (e.g. 1.5) increase creativity. Default is 1."},"tool_choice":{"type":"string","description":"Controls tool calling behavior. 'auto' lets the model decide, 'none' disables tools, 'required' forces a tool call, or pass {\"type\": \"function\", \"function\": {\"name\": \"...\"}} to force a specific tool."},"top_logprobs":{"type":"number","description":"How many of the most likely tokens (0-20) to return log probabilities for at each position. Requires logprobs to be true."},"bad_token_ids":{"type":"array","description":"Array of token IDs that should never appear in the output."},"chat_template":{"type":"string","description":"Custom Jinja2 template for formatting the conversation. Overrides the model's default chat template."},"early_stopping":{"type":"boolean","description":"In beam search, stop as soon as the required number of complete candidates are found."},"length_penalty":{"type":"number","description":"Penalty applied during beam search. Values > 1.0 favor longer sequences, < 1.0 favor shorter ones."},"stop_token_ids":{"type":"array","description":"Array of token IDs that will cause generation to stop when produced."},"stream_options":{"type":"object","description":"Options for streaming. Use {\"include_usage\": true} to get a final chunk with token usage statistics."},"response_format":{"type":"object","description":"Constrain the output format. Use {\"type\": \"json_object\"} for JSON mode, or {\"type\": \"json_schema\", \"json_schema\": {\"name\": \"...\", \"schema\": {...}}} for structured outputs with a specific schema."},"presence_penalty":{"type":"number","description":"Penalize tokens based on whether they've appeared at all. Range -2.0 to 2.0. Positive values encourage the model to explore new topics. Default: 0."},"reasoning_effort":{"type":"string","description":"Controls thinking depth for reasoning models. Options: 'low', 'medium', 'high'. Default: 'medium'. Higher effort uses more tokens but produces more thorough reasoning. Supported on DeepSeek V3/V3.1, GLM 4.6/4.7, and Kimi K2 Thinking."},"frequency_penalty":{"type":"number","description":"Penalize tokens based on how often they've appeared so far. Range -2.0 to 2.0. Positive values reduce repetition. Default: 0."},"add_special_tokens":{"type":"boolean","description":"If true, adds special tokens (like BOS) to the input. Default: true."},"chat_template_args":{"type":"object","description":"Additional arguments passed to the chat template as template variables."},"repetition_penalty":{"type":"number","description":"Multiplicative penalty for repeated tokens. Values > 1.0 discourage repetition, < 1.0 encourage it."},"parallel_tool_calls":{"type":"boolean","description":"Whether the model can make multiple tool calls in parallel in a single response. Default: true."},"skip_special_tokens":{"type":"boolean","description":"If true, special tokens are removed from the output text. Default: true."},"disaggregated_params":{"type":"object","description":"Advanced parameters for distributed inference. Only relevant for disaggregated serving configurations."},"add_generation_prompt":{"type":"boolean","description":"If true, applies the model's generation prompt template. Usually needed for chat models."},"truncate_prompt_tokens":{"type":"number","description":"Truncate the prompt to this many tokens if it exceeds the limit, keeping the most recent tokens."},"include_stop_str_in_output":{"type":"boolean","description":"If true, includes the stop string in the generated output rather than trimming it."},"spaces_between_special_tokens":{"type":"boolean","description":"If true, adds spaces between special tokens in the detokenized output."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false}}}}},"description":"Send a conversation to a model and get a completion back. Works exactly like the OpenAI chat completions endpoint. Pass messages and a model slug, get a response with the assistant's reply. Supports streaming for real-time token delivery, tool calling for function execution, structured outputs via response_format, and controllable reasoning depth on supported models. | ERROR: Unable to calculate price.","lastUpdated":"2026-09-14T18:46:23.487Z","x402Version":2}]}}