provider::sarvam::abort
Cancel the in-flight upstream stream for a request_id (router::abort fan-out), stopping billed generation immediately.
- request_idstringrequired
- abortedbooleanrequired
provider-sarvam
v0.1.1Sarvam AI provider worker; implements provider::sarvam::stream for the Sarvam chat models plus provider::sarvam::transcribe (Saaras) and provider::sarvam::speak (Bulbul) behind llm-router.
Install
bash
iii trigger compose::add worker=provider-sarvamRun in your project with the iii engine running. Exact versions are immutable and digest-pinned.
Functions7
Function
provider::sarvam::count_tokens
Estimate prompt tokens for {model, system_prompt?, tools?, messages} locally with tiktoken; never runs the model and costs nothing.
- messagesany of[]required
Wire agent messages, the same shape `provider::sarvam::stream` accepts. Must be non-empty.
any of (4)Variant 1- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- error_kindany of
Show 2 nestedHide nested
any of (2)Variant 1valuestringenum auth_expired, rate_limited, context_overflow, transient, permanentVariant 2valuenull - error_messagestring
- modelstringrequired
- native_stop_reasonstring
- providerstringrequired
- rolestringrequiredenum assistant
- stop_reasonstringrequiredenum end, length, function_call, aborted, error
- timestampinteger· int64required
- usageany of
Show 2 nestedHide nested
any of (2)Variant 1- cache_readinteger· uint64min 0
- cache_writeinteger· uint64min 0
- cost_usdnumber· double
- inputinteger· uint64min 0
- outputinteger· uint64min 0
- reasoninginteger· uint64min 0
Variant 2valuenull - warningsstring[]
Variant 2- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- detailsunknownrequired
- function_call_idstringrequired
- function_idstringrequired
- is_errorbooleanrequired
- rolestringrequiredenum function_result
- timestampinteger· int64required
Variant 3- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- custom_typestringrequired
- detailsunknown
- displaystring
- rolestringrequiredenum custom
- timestampinteger· int64required
Variant 4- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- rolestringrequiredenum user
Single-variant role tags: exact-match on deserialize, correct wire string on serialize, and they let `AgentMessage` be an untagged union.
- timestampinteger· int64required
- modelstringrequired
Model id the prompt targets; reported back unchanged.
- system_promptstring
System prompt counted as its own wire message when present.
- toolsobject[]
Function invocation schemas; each serialized schema counts toward the total.
- descriptionstringrequired
- execution_modestring
- labelstring
- namestringrequired
- parametersunknownrequired
- estimatorstringrequired
Always `tiktoken`: a local tokenizer produced the estimate.
- modelstringrequired
- tokensinteger· uint64requiredmin 0
Estimated prompt tokens for the assembled request.
provider::sarvam::on_router_ready
Internal: router::ready subscriber that re-declares this provider and refreshes its catalog.
Empty object
- okbooleanrequired
provider::sarvam::refresh_models
Reconcile the curated Sarvam catalog slice, chat and speech models, through the router (Sarvam has no models-listing endpoint); returns the count written.
Empty object
- countinteger· uintrequiredmin 0
- okbooleanrequired
provider::sarvam::speak
Text to speech on Sarvam Bulbul behind router::speak: text, a speaker name and a language in, base64 audio out (mp3, wav, pcm16, opus).
- formatstring
`mp3` (default), `wav`, `pcm16`, `opus`.
- languagestring
Language of the text (`hi`, `hi-IN`, ...); English when omitted.
- modelstring
Text-to-speech model id; `bulbul:v3` when omitted.
- speednumber· double
Speaking-rate multiplier, 0.5 to 2.0; 1.0 is the voice's own pace.
- textstringrequired
Text to speak, up to 2500 characters. Write Indic words in their own script for natural speech.
- voicestring
Speaker name (`shubh`, `shreya`, `manan`, `ishita`, ...; the v2 voices `anushka`, `abhilash`, ... only with `bulbul:v2`).
- audio_base64stringrequired
- mimestringrequired
- modelstringrequired
- voicestringrequired
The speaker used.
provider::sarvam::stream
Stream a Sarvam chat completion: resolve credentials, call the upstream Chat Completions API, and relay AssistantMessageEvent frames to writer_ref.
- cache_intentany ofany of (2)Variant 1
- surface_digeststringrequired
Variant 2valuenull - max_output_tokensinteger· uint64min 0
- messagesany of[]requiredany of (4)Variant 1
- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- error_kindany of
Show 2 nestedHide nested
any of (2)Variant 1valuestringenum auth_expired, rate_limited, context_overflow, transient, permanentVariant 2valuenull - error_messagestring
- modelstringrequired
- native_stop_reasonstring
- providerstringrequired
- rolestringrequiredenum assistant
- stop_reasonstringrequiredenum end, length, function_call, aborted, error
- timestampinteger· int64required
- usageany of
Show 2 nestedHide nested
any of (2)Variant 1- cache_readinteger· uint64min 0
- cache_writeinteger· uint64min 0
- cost_usdnumber· double
- inputinteger· uint64min 0
- outputinteger· uint64min 0
- reasoninginteger· uint64min 0
Variant 2valuenull - warningsstring[]
Variant 2- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- detailsunknownrequired
- function_call_idstringrequired
- function_idstringrequired
- is_errorbooleanrequired
- rolestringrequiredenum function_result
- timestampinteger· int64required
Variant 3- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- custom_typestringrequired
- detailsunknown
- displaystring
- rolestringrequiredenum custom
- timestampinteger· int64required
Variant 4- contentone of[]required
Show 7 nestedHide nested
one of (7)Variant 1- textstringrequired
- typestringrequiredenum text
Variant 2- attachment_idstring
Optional link to the stored original in the session-manager attachment store. Transcript bookkeeping for lazy readers only: the harness clears it before `router::chat`, and no provider mapping reads it. Tolerated here so a block that still carries it deserializes instead of failing the request; omitted on the wire when absent.
- datastringrequired
- mimestringrequired
- typestringrequiredenum image
Variant 3- attachment_idstringrequired
- mimestringrequired
- namestringrequired
- sizeinteger· uint64requiredmin 0
- typestringrequiredenum file
Variant 4- signaturestring
- textstringrequired
- typestringrequiredenum thinking
Variant 5- datastringrequired
- typestringrequiredenum redacted_thinking
Variant 6- argumentsunknownrequired
- function_idstringrequired
- idstringrequired
- typestringrequiredenum function_call
Variant 7- contentunknown[]required
- function_call_idstringrequired
- is_errorboolean
- typestringrequiredenum function_result
- rolestringrequiredenum user
Single-variant role tags: exact-match on deserialize, correct wire string on serialize, and they let `AgentMessage` be an untagged union.
- timestampinteger· int64required
- modelstringrequired
- model_metaany ofany of (2)Variant 1
- context_windowinteger· uint64requiredmin 0
- display_namestring
- idstringrequired
- input_limitinteger· uint64min 0
- max_output_tokensinteger· uint64requiredmin 0
- pricingany of
Show 2 nestedHide nested
any of (2)Variant 1- cache_readnumber· double
- cache_writenumber· double
- inputnumber· double
- outputnumber· double
Variant 2valuenull - providerstringrequired
- reasoning_effortsobject[]
Show 2 nestedHide nested
- descriptionstring
- effortstringrequired
- speechany of
Set on speech models only; see [`SpeechModel`].
Show 2 nestedHide nested
any of (2)Variant 1- languagesstring[]
BCP-47 tags of the languages the model handles; empty when the provider does not say.
- modalityone ofrequired
What a speech model does. Chat models carry no `speech` block.
Show 2 nestedHide nested
one of (2)Variant 1valuestringenum sttVariant 2valuestringenum tts - streamingboolean
Realtime input (stt) or streamed audio output (tts) is available.
Variant 2valuenull - supports_cacheboolean
- supports_structured_outputboolean
- supports_thinkingboolean
- supports_thinking_offboolean
Whether `thinking_level: off` can switch the model's reasoning off. `Some(true)`: a native off switch exists. `Some(false)`: the model always reasons, or the provider has no switch. `None`: the provider does not know; consoles show the choice disabled.
- supports_toolsboolean
- supports_visionboolean
- supports_xhighboolean
- thinking_budgetsobject
Variant 2valuenull - provider_optionsunknown
- resolution_keystring
- response_formatany ofany of (2)Variant 1
- schemaunknown
- typestringrequired
Variant 2valuenull - session_idstring
Stable conversation identity for provider cache affinity.
- system_promptstring
- system_sectionsobject[]
Ordered sections behind `system_prompt` (always forwarded alongside the flat string, which equals the sections joined with "\n\n").
- cache_boundaryboolean
- textstringrequired
- thinking_levelany ofany of (2)Variant 1valuestringenum off, minimal, low, medium, high, xhighVariant 2valuenull
- toolsobject[]
- descriptionstringrequired
- execution_modestring
- labelstring
- namestringrequired
- parametersunknownrequired
- writer_refobjectrequired
- access_keystringrequired
- channel_idstringrequired
- directionstringrequiredenum read, write
- okbooleanrequired
provider::sarvam::transcribe
Speech to text on Sarvam Saaras behind router::transcribe: base64 audio in, text with timed segments and the detected language out; 22 Indian languages and English.
- audio_base64stringrequired
The audio, base64. WAV, MP3, AAC, OGG, OPUS, FLAC, M4A, WebM.
- languagestring
Language hint (`hi`, `hi-IN`, ...); detected when omitted.
- mimestring
MIME type of the audio; `audio/wav` when omitted.
- modelstring
Speech-to-text model id; `saaras:v3` when omitted.
- promptstring
Accepted for the shared contract; Saaras takes no prompt.
- duration_secsnumber· double
- languagestring
Language Saaras detected or was told, as `hi-IN`.
- modelstringrequired
- segmentsobject[]
Sentences, cut at punctuation or a pause, with word timings.
- end_secsnumber· double
- start_secsnumber· double
- textstringrequired
- textstringrequired
Triggers0
No triggers registered