Resources
Changelog
Latest updates, new features, and improvements to the CallMissed API.
November 2026
CRM integration API (2026-11-17)
- Create-or-update.
POST /api/v1/contacts/upsert,POST /api/v1/companies/upsertandPOST /api/v1/crm/leads/upsertcreate a record or update the one that already carries your id, so a sync can be re-run safely. Contacts match on your external id, phone or email; companies on your external id, domain or name; leads onexternal_ref. The response says which happened (created,matched_on). See Contacts, Companies and Leads. - Look up by your own id.
GET /api/v1/contacts?external_id=hubspot:123and the same on companies;GET /api/v1/crm/leads?external_ref=…for leads. - Changed since.
updated_afteron the contact, company, lead, deal and task lists returns the records changed after a time, oldest change first. - CRM change webhooks. Eighteen new events,
contact|company|lead|deal|task|note×created|updated|deleted, sent for every change whoever made it, with asourcefield and the full record. See Webhooks. - Call transcript by call id.
GET /api/v1/telephony/calls/{call_id}/transcript(format=json|txt|srt, scopetelephony:read). See Telephony. - New guide: Connect your CRM.
Legacy voice WebSocket removed (2026-11-11)
wss://api.callmissed.com/ws/voice-agentis removed. For a voice agent over a plain WebSocket, use the Managed Voice Agent atwss://api.callmissed.com/v2/voice/agent: it sends aConversationTextevent for each finished caller turn. For WebRTC, use voice sessions. The Real-time STT page, which documented the removed socket, now redirects to the Managed Voice Agent. File transcription on Speech to Text is unchanged.
ElevenLabs voices and Scribe transcription (2026-11-07)
- Nine ElevenLabs text-to-speech models under their own IDs on
POST /v1/audio/speechand in voice agents and voice sessions (tts_model):eleven_v4,eleven_v4_turbo,eleven_v3,eleven_v3_conversational,eleven_multilingual_v2,eleven_flash_v2_5,eleven_turbo_v2_5,eleven_flash_v2andeleven_turbo_v2. v4 speaks 91 languages and v3 85, both including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia and Urdu; Flash v2.5 speaks 32 including Hindi and Tamil.eleven_v4,eleven_v3andeleven_multilingual_v2are $0.8333 per 10K characters, the rest $0.4167. See Text to Speech. - One shared voice library. Pass a premade name (
sarahdefault,george,brian, …) or any ElevenLabs voice ID, including your cloned voices, asvoice.languagetakes a base code (hi) and enforces the language on every model excepteleven_multilingual_v2;speedclamps to 0.7–1.2;mp3,wav,pcm,opus,mulawandalawoutput. v3 and v4 perform audio tags such as[laughs]. See Voices. - ElevenLabs Scribe speech-to-text.
scribe_v2andscribe_v2_medical($0.2292 per hour) transcribe files in 100 languages with automatic language detection onPOST /v1/audio/transcriptions;scribe_v2_realtime($0.4063 per hour) is the streaming model for voice agents (stt_model). See Speech to Text. - Paid plans only. The catalogue is now 159 models: 50 speech-to-text and 25 text-to-speech.
Kimi K3.1 Pro (2026-11-06)
kimi-k3.1-pro(Moonshot AI) is Moonshot's most capable open-weight model, natively multimodal and built for agentic work: coding, 3D creation, financial research and tool use. 1,048,576-token context window, 131,072 tokens of default max output, image input, tool calling, JSON mode (response_format: {"type": "json_object"}) and streaming. Output is text.- It thinks by default.
reasoning_effortaccepts"none"(thinking off),"low","high"and"max";"minimal"runs as"low","medium"as"high"and"xhigh"as"max". See the reasoning_effort matrix. - Priced at $2.00 input / $10.00 output per 1M tokens, with cached input at $0.20. Paid plans only; it is not in the free tier.
- Images go in as base64 data URIs; we fetch and inline
https://image URLs for you. - The catalogue is now 147 models: 73 LLMs.
Voice calls keep going through rate limits (2026-11-02)
- When a voice agent's model cannot answer a turn, for example because of a rate limit,
sarvam-105banswers it, and if that fails too,gpt-4odoes. Before, a call whose model andsarvam-105bboth failed could end. A turnsarvam-105banswered is billed at its own rate; a turngpt-4oanswered is billed at your agent's model rate, and usage showsgpt-4oas the model that answered. On an agent withhosting: "india",gpt-4ois used only while it is processed in India. See Voice agent. - When many calls start at the same moment, their speech connections are opened a moment apart, so fewer are refused for opening too fast. A refused one moves to the backup speech provider: listening at once, and a reply after one quick retry.
Numbers nothing answers play a short message (2026-11-02)
- An inbound call to a number with no agent, or whose agent is switched off, and no call menu, call flow, call queue or agent squad is now answered with "Sorry, this number isn't taking calls right now. Please try again later." and then ends. Before, a number with no agent was answered by a generic assistant, and one whose agent was switched off was not picked up. The message plays in the number's own language setting when it has one, else English.
- The call is billed like any other short inbound call: carriage for its length, plus the ₹1 a minute platform fee at its 30-second minimum. See Telephony and Bots.
GLM 5.3 Flash and DeepSeek V4.1 Flash 1017 (2026-11-01)
glm-5.3-flash(Z.ai) is a fast, low-cost GLM for coding agents and tool use, with a 1,048,576-token context window, image input, tool calling, structured output and streaming. It always reasons:reasoning_efforttakes"low","high"or"max", with"high"as the default;"none"and"minimal"map to"low","medium"to"high"and"xhigh"to"max". In our tests with"low"the first token arrived in about 0.4 to 0.5s. $0.229 per 1M input tokens, $0.760 per 1M output tokens ($0.052 cached input). Paid plans only.deepseek-v4.1-flash-1017(DeepSeek) is the October 17 snapshot of DeepSeek V4.1 Flash, with a 1,048,576-token context window, image input, tool calling (includingtool_choice: "required") and streaming. It reasons at"high"by default andreasoning_effort: "none"switches thinking off (first token in about 0.25 to 0.6s in our tests). $0.427 per 1M input tokens, $1.771 per 1M output tokens ($0.0104 cached input), the same asdeepseek-v4.1-flash. Paid plans only.- Images go in as base64 data URIs; we fetch and inline
https://image URLs for you. When you omitmax_tokenswe send 16,384, since reasoning tokens count toward the limit. - The catalogue is now 146 models: 72 LLMs.
October 2026
Deepgram Think-Fast and phoneLLM mini chat models (2026-10-31)
deepgram-think-fast(Deepgram) anddeepgram-phonellm-mini(Pipecat) are early-access chat models for voice agents, onPOST /v1/chat/completionsand as thellm_modelof a voice agent. 32,768-token context, tool calling and streaming, text only.deepgram-think-fastsupportsreasoning_effort(nonedefault,minimal,low,medium,high);deepgram-phonellm-minidoes not reason. Both are $0.3646 per 1M input tokens and $0.9375 per 1M output tokens, paid plans only, and not a default anywhere.- Training on your data. Conversations on
deepgram-think-fastare used by the provider to improve its models; the opt-out does not apply to it.deepgram-phonellm-miniis excluded from the provider's model training. - Processed outside India. India-only keys and accounts get
region_unavailable, and voice agents withhosting: "india"cannot select them.tool_choicetakes only"auto"or"none", andresponse_formatreturns400 unsupported_parameter. See Models. - Languages. In our tests
deepgram-think-fastwas reliable in English, Hindi, Marathi, Telugu and Kannada, anddeepgram-phonellm-minionly in English and Hindi. Validating a voice agent's config now flags other languages (an error fordeepgram-phonellm-mini, a warning fordeepgram-think-fast). - The catalogue is now 144 models: 70 LLMs.
Gnani Prisma v3, and Prisma v2.5 retired (2026-10-30)
gnani-prisma-v3.0is Gnani's newest India-first telephony speech-to-text model: English plus 9 Indian languages (hi-IN,bn-IN,ta-IN,te-IN,kn-IN,ml-IN,mr-IN,gu-IN,pa-IN,en-IN), automatic language detection withlanguage: "indic-auto", mixed-language speech and keyterm boosting. It runs real-time and batch. Price is $0.2813 / hour, the same as v2.5. Paid plans only.POST /v1/audio/transcriptions.languagetakes one of the 10 codes, a comma-separated list of up to 4 of them, orindic-auto; a base code such ashiis read ashi-IN. Audio is limited to 30 seconds per request (v2.5 allowed 60); longer audio returns400 audio_too_long.- Voice agents and sessions. On
gnani-prisma-v3.0,language: "multi"follows a multilingual caller (it detects the language, so the voice follows), and per-agentstt_keytermsare applied. It is processed in India, so it stays available in India mode. gnani-prisma-v2.5is retired. The ID keeps working on the API, in voice agents and in saved agents. It is answered bygnani-prisma-v3.0, the response keeps the ID you sent, it keeps its price ($0.2813 / hour) and it is no longer listed byGET /api/v1/models. The same 30-second per-request limit now applies. Agents that set the old code-mixed codesen-hi-in-cmoren-hi-IN-latnkeep working. See Retired and deprecated models.- The catalogue size is unchanged: one model added, one retired.
Deepgram updates (2026-10-30)
- Managed voice-agent models.
deepgram-voice-anthropic-claude-sonnet-5-5(Advanced, $0.1698/min),deepgram-voice-anthropic-claude-haiku-5-5(Standard, $0.07813/min), and the early-accessdeepgram-voice-deepgram-think-fastanddeepgram-voice-deepgram-phonellm-mini-alpha-2-fp8(Standard). Conversations ondeepgram-voice-deepgram-think-fastare used by the provider to improve its models. - Speech to text. New
deepgram-nova-3-pharma(English only) for drug names.deepgram-nova-3-medicalnow acceptslanguage=multi(10 languages).POST /v1/audio/transcriptionstakes a repeatablelanguage_hintfield fordeepgram-nova-3withlanguage=multi. - Pricing by mode.
deepgram-nova-3,-medicaland-pharmaare $0.325 / hour for files and $0.4792 / hour on live voice sessions, or $0.5729 / hour when the session's language ismulti(-pharmais English only, so always $0.4792) (previously $0.3021 / hour for both).deepgram-flux-general-enis $0.4792 / hour (previously $0.4063). - Flux TTS on
/v1/audio/speech.deepgram-flux-tts($0.4688 / 10K characters) now has 266 voices in 42 languages, including Hindi, Tamil, Telugu, Kannada, Marathi, Gujarati, Bengali and Urdu (32 languages are early access), and supportsstream: true. Input is capped at 2000 characters, and at 400 without streaming. - The catalogue is now 142 models: 47 speech-to-text and 16 text-to-speech.
Preview: Microsoft AI speech models (2026-10-30)
- Text to speech.
mai-voice-2.1($0.2292 / 10K characters) is Microsoft AI's most expressive voice model, for narration and long-form audio.mai-voice-2.1-flash($0.1563 / 10K characters) is built for low latency and real-time voice agents. Both have 97 voices across 23 languages, including Hindi (hi-in-arjun,hi-in-dhruv,hi-in-grant,hi-in-harper,hi-in-kavya,hi-in-priya) and Indian English (en-in-dhruv,en-in-priya). Plain text only, speed 0.5 to 2.0. They work onPOST /v1/audio/speechand in voice agents and voice sessions (tts_model). See Voices. - Speech to text.
mai-transcribe-2($0.375 / hour) transcribes files in 60 languages with automatic language detection and Hinglish code-switching, up to 2 hours per file, onPOST /v1/audio/transcriptions. It is not available in voice sessions or translation. See Speech to Text. - All three are preview. Microsoft ships them with no SLA and may change or retire them at short notice. If one is retired, its ID keeps working and is answered by a named successor, as in Retired and deprecated models, so an agent that uses it keeps working but may sound different. Use generally available models for production-critical agents. They are paid-plan only, are never a default, are not processed in India, and the voices cannot be used in
tts_fallbacks.GET /api/v1/modelsmarks them withpreview: true. - The catalogue is now 137 models: 46 speech-to-text and 16 text-to-speech.
API behaviour fixes
- Ending a voice session made by another key now needs
telephony:read.DELETE /v1/voice/sessions/{id}follows the same rule as reading a session: a key can always end the sessions it created, including calls it placed withPOST /api/v1/telephony/calls, and needstelephony:readfor sessions the console or another key created. Without it the call returns403. - Key budget refusals say so. When an API key's own spending budget, not the account balance, cannot cover a request, the response is now
budget_exceededinstead ofinsufficient_credits. n> 1 near the time limit. A non-streaming chat completion that reaches the request time limit after some of itsnchoices are finished now returns those choices, billed as delivered, instead of an error.- Audio of unknown length. Speech-to-text uploads whose duration cannot be read from the file are no longer refused up front for a worst-case estimate; they are billed on the duration actually processed.
Hosted in India voice agents
- New
hostingsetting. Sethosting: "india"in a voice agent's config, or Where calls run → Hosted in India in the console's Voice card. Speech recognition, the model, the voice, their backups, knowledge-base and memory search, and post-call analysis, notes, scoring and contact memory then all run in India. - Models you can choose in India mode. Speech to text:
saaras:v4,gnani-prisma-v2.5,microsoft-speech-sttand the Deepgram Nova and Flux models (Whisper excluded). Models:gemma-4-31b,sarvam-105b,sarvam-105b-conversations,glm-5.3anddeepseek-v4.1-flash. Voices:bulbul:v3,bulbul:v4-flash,gnani-timbre-v3.0,microsoft-neural-ttsanddeepgram-aura-2/deepgram-aura-1. Of the voice plans, onlyt1qualifies. Speech-to-speech models are not available. - Saving is checked. Saving an India-hosted agent with a model outside this list returns
422naming the model.GET /api/v1/bots/config-schemalists the allowed models underindia_hosting, and each plan carrieshosted_in_india. hosting: "global"runsgemma-4-31bon a global host first, with India as its fallback; nothing else changes. Withouthosting, agents behave as before. Prices are the same in every mode.hosted_in_indiain the model catalogue now means processed in India on every request. Models served from a global pool are no longer flagged, even when their endpoint is in India.
New voice-agent models: Microsoft Speech and Microsoft Neural voices
- Speech to text.
microsoft-speech-stt($1.0417 / hour) is Microsoft's real-time streaming recognizer, processed in India. It hears 81 languages (148 locales), including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, Assamese, Urdu, Bhojpuri and Indian English, one language per call. - Text to speech.
microsoft-neural-tts($0.1563 / 10K characters), processed in India, has 57 voices across 13 languages, with plain-text input and a speaking-speed control (tts_speed, 0.5 to 2.0). - Voice sessions only. Both run inside voice agents and voice sessions.
POST /v1/audio/transcriptionsandPOST /v1/audio/speechreturn400for them. See Voices and Speech to Text. - The catalogue is now 134 models: 45 speech-to-text and 14 text-to-speech.
New voice-agent models: AssemblyAI, Inworld, Rime, Fish Audio, Gradium and Deepgram Flux TTS
- Speech to text.
assemblyai-universal-3.6-pro($0.4688 / hour) is AssemblyAI's newest streaming model with built-in turn detection and Hindi, Marathi, Urdu and Indian English among its languages.inworld-stt-1($0.1563 / hour) is a low-cost English-only model. - Text to speech.
deepgram-flux-tts($0.4688 / 10K characters, 16 English voices),rime-coda($0.5208, 8 languages including Hindi),inworld-tts-2($0.2604) andinworld-tts-2-flash($0.1563) with 94 languages including 11 Indian languages,fish-audio-drama-3($0.5208, 13 languages) andgradium-tts-beta($0.50, 5 languages). - Voice sessions only. All eight run inside voice agents and voice sessions.
POST /v1/audio/transcriptionsandPOST /v1/audio/speechreturn400for them. See Voices and Speech to Text. - The catalogue is now 132 models: 44 speech-to-text and 13 text-to-speech.
Models moved, retired and deprecated
- Same IDs, new hosting.
kimi-k2.5,kimi-k2.6,kimi-k2.7-code,gpt-oss-120b,DeepSeek-V4-ProandDeepSeek-V4-Flashkeep their IDs and prices.kimi-k2.5now has a 262,144-token context window andgpt-oss-120b131,072.DeepSeek-V4-ProandDeepSeek-V4-Flashtake 1,000,000 input tokens. - Price updated 2026-10-17.
DeepSeek-V4-Proinput is now $1.813 per 1M tokens (was $1.375) and cached input $0.151 (was $0.04583); output is unchanged at $4.125.DeepSeek-V4-Flashcached input is now $0.02917 per 1M (was $0.01458); input and output are unchanged. - Retired IDs keep working.
glm-4.7-flash,glm-5.2,nemotron-3-super,gemma-4-26b-a4b-it,mistral-small-3.1,flux-2-klein-9b,lucid-origin,phoenix-1.0,sdxl-lightning,dreamshaper-8-lcm,aura-2-en,aura-2-es,melotts,nova-3andwhisper-large-v3-turboare no longer listed. Requests that name them are answered by a successor model and the response keeps the ID you sent. Most keep their price;gemma-4-26b-a4b-it,mistral-small-3.1,sdxl-lightning,dreamshaper-8-lcm,melottsandwhisper-large-v3-turbonow bill at their successor's price. See Retired and deprecated models for each successor and price. - Free plan. The retired LLM, speech-to-text and text-to-speech IDs stay free. The free plan no longer includes an image model: a free key that requests an image gets
403 model_not_available. The default image model forPOST /v1/images/generationsand social posts is nowflux-2-pro. The free tier is now 11 listed models and the catalogue is 124. - Deprecated, sunset 2026-11-16:
gpt-4o,gpt-4.1,gpt-5.5,gpt-5.6-solandgpt-5.6-terra(successorgpt-6-sol);gpt-5-miniandgpt-5.6-luna(gpt-6-luna);gemini-3.5-flash,gemini-3.6-flashandgemini-3.7-flash(gemini-3.8-flash);gemini-3.1-flash-lite(gemini-3.5-flash-lite);gpt-realtime,gpt-realtime-1.5andgpt-realtime-2(gpt-realtime-2.1);gpt-realtime-mini(gpt-realtime-2.1-mini);gpt-image-1.5andgpt-image-2(gpt-image-2.5-flare);flux-1.1-pro(flux-2-pro); and the older Deepgram speech-to-text IDs (deepgram-nova,deepgram-nova-2,deepgram-enhanced,deepgram-basetodeepgram-nova-3; their medical variants todeepgram-nova-3-medical; their phonecall, meeting, finance, conversationalai, voicemail and video variants to the matchingdeepgram-nova-2-*model). The full table is in Retired and deprecated models. Until then they are served as themselves; responses carryDeprecation,SunsetandLinkheaders, and the catalogue marks themdeprecated: truewithsunset_dateandsuccessor. From 2026-11-16 a request that names one is answered by and billed as its successor. aura-2-enandaura-2-eskeep their voices but now accept up to 2,000 characters per request, the limit of the model that answers them.
Gnani Timbre v3, and older speech models retired
gnani-timbre-v3.0replacesgnani-timbre-v2.0. It has 12 voices (defaultShivani), every voice speaks all 10 Indian languages plus Hinglish, it streams, and the text accepts expressive audio tags such as<laugh>and<pauses>. Price is unchanged at $0.27 per 10K characters. See Text to Speech. Requests naminggnani-timbre-v2.0now return the unknown-model error.bulbul:v2andsaaras:v3are retired. Usebulbul:v3orbulbul:v4-flashfor speech, andsaaras:v4for transcription (same languages, modes and price).saaras:v4is now the default whenmodelis omitted. Voice sessions that still namesaaras:v3orsaarika:v2.5are served assaaras:v4.- The catalogue is now 139 models and the free tier is 26.
New models: DeepSeek V4.1 Flash and Bulbul V4 Flash
deepseek-v4.1-flash— a 1M-token reasoning model with tool calling and text-only input. It always reasons:reasoning_efforttakes"low","high"or"max"(the default). Pricing per 1M tokens is $0.427 in / $1.771 out ($0.0104 cached input). Paid plans only.bulbul:v4-flash— low-latency Indic text to speech with 222 persona voices (<name>_<language>_<style>, defaultshubh_enhi_ads) across 9 Indian languages and Hinglish, at $0.2083 per 10K characters. It is on the free tier. Input is capped at 2,500 characters.ml-INandod-INare not available on it; usebulbul:v3.- The catalogue is now 140 models and the free tier is 27.
flux-2-dev removed
flux-2-devhas been removed: every request to it was failing upstream.POST /v1/images/generationswith"model": "flux-2-dev"now returns404with codemodel_not_found. Useflux-2-klein-9b, which is also free.nano-banana-2andflux-1.1-pronow fall back toflux-2-klein-9b. The free tier is 26 models (5 image). Past images and usage records are unchanged.
Nova Sonic models removed
nova-sonic-2andnova-sonichave been removed from the catalog.GET /api/v1/modelsno longer lists them, and a voice session that names either returns422. Usegpt-realtime-2.1-minifor speech-to-speech. An agent still configured with either model keeps answering calls on the standard STT, LLM and TTS pipeline; past usage and session cost records are unchanged.
Upstream failures now return 503 with Retry-After
- Failures of a model or channel behind the API, and gateway timeouts, now return
503(with aRetry-Afterheader) instead of502or504. Our CDN replaces an origin502or504with its own HTML error page, so your client never saw the JSON error body or its reason code. Reason codes and retry advice are unchanged: only the status moved. A timeout that may have applied the action (for example a social action or a Facebook publish) is still ambiguous, so check before retrying. See Errors.
New models: Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5
claude-opus-5-5,claude-sonnet-5-5andclaude-haiku-5-5— Anthropic's Claude 5.5 family, available on the Pro plan and higher (free and Starter keys get403 model_not_available). 1M context, 128K max output, text + image input, reasoning and tool calling.- Pricing per 1M tokens — Opus $4.167 in / $20.83 out ($0.2083 cached input); Sonnet $2.083 in / $10.42 out ($0.1042 cached); Haiku $0.1042 in / $0.5208 out ($0.01042 cached), rising to $0.5208 / $2.604 ($0.05208 cached) for prompts over 100K tokens.
reasoning_effort— acceptslow,medium,high,xhighandmax;noneandminimalrun aslow.temperature,top_pandtop_kare ignored. See API speed and function calling for theanthropic_thinkingfield to send back with tool calls.
Nova Sonic models under maintenance
nova-sonic-2andnova-sonicare under maintenance:POST /v1/voice/sessionsreturns503with a message naming the alternative, andGET /api/v1/modelsshowsstatus: "maintenance". Usegpt-realtime-2.1-minifor speech-to-speech. An agent still configured with either model keeps answering calls on the standard STT, LLM and TTS pipeline.
Usage API — costs in US$, prompt-cache totals
cost_usdon/v1/usage/summary,/v1/usage/logsand/v1/usage/logs.csv(and theget_usage_summary/list_usage_logsMCP tools) is now the US$ you were billed at the published rate (1 credit = ₹1, US$1 = ₹96). It was previously reported in internal billing units (0.01per credit), about 4% below the US$ amount; credits = US$ × 96. Past rows are converted the same way, so a window spanning the change stays consistent./v1/usage/summaryreports prompt-cache usage:totals.total_cache_read_tokens,totals.total_cache_creation_tokens, andcache_read_tokens/cache_creation_tokensper service.input_tokenskeeps its meaning (the uncached part of the prompt).
Per-model parameters follow each model's documentation
- Output limits —
GET /api/v1/modelsnow listsmax_output_tokenswhere a model documents one, andmax_tokensabove it returns400 max_tokens_too_largeon/v1/chat/completions,/v1/responsesand/v1/messages. Thegemini-*models now allow up to 65,536 output tokens (previously capped at 8,192), and an omittedmax_tokensleaves the model's own default. reasoning_effort—xhighandmaxnow reach every model instead of being cut tohighfirst; each model maps them to its own top level.DeepSeek-V4-Pro/-Flashandglm-5.2now honour their levels,nemotron-3-superswitches to its low-effort mode forlow/none,sarvam-105bswitches thinking fully off fornone, andgpt-5-miniusesminimal. See API speed.- Sarvam — when you omit
max_tokens, we send 4,096 (16,384 forglm-5.3) so thinking no longer cuts answers short at 2,048. Aglm-5.3orgemma-4-31brequest over 10 MB returns413. - Models —
gpt-4.1serves a 300,000-token context window. The realtimegpt-realtime-2*models take 32,000 input and 4,096 output tokens.nova-sonicwas retired upstream on 2026-09-14 and returns503; usenova-sonic-2. - Images and speech — image sizes outside a model's range, and
negative_promptonlucid-origin, return400.gpt-4o-mini-ttshas 13 voices and rejects an unknown voice with400.gpt-4o-transcribe-diarizereturns speakersegmentswithresponse_formatverbose_jsonordiarized_json; it is no longer accepted as a voice-sessionstt_model(422), because live transcription cannot label speakers. grok-4.3 reasoning tokens now count as output tokens, and its images must have at least 512 pixels.
Email domains — neutral 503 reason
- The
503returned by the email domain routes when provisioning or verification is temporarily unavailable now carriesreason: "provider_unavailable". Deployments still being upgraded may return the olderacs_unavailablefor the same condition; status, body shape and retry advice are identical, so match both strings. See Email limits.
Voice session webhooks
voice_session.endedandvoice_session.failednow fire exactly once per session, on every way a session can end (the agent hanging up,DELETE, the session timing out), and only after the end has been saved. If two end signals arrive together, the first one decidesend_reasonandduration_seconds.- A session that ends because the agent hit an error (
end_reason: "agent_error") now has statusfailedand firesvoice_session.failedon every path; it previously firedvoice_session.endedfor some sessions. See Webhooks.
Speech-to-text error codes
/v1/audio/transcriptionsand/v1/audio/translationsnow return400 invalid_requestfor a problem with the request (unsupported audio, a streaming-only or unknown model),429 rate_limit_exceededwhen rate limited, and503 service_unavailablewhen transcription is temporarily unavailable, the same code/v1/audio/speechuses. See Speech-to-Text.
Batch API, zero data retention, per-end-user budgets and prompt caching
- Batch API — OpenAI-compatible
POST /v1/filesandPOST /v1/batches: upload a JSONL file of requests, run it asynchronously, and download the results. Gated by the key'sllmpermission. See Batch API. - Zero data retention — send
"provider": {"zdr": true}to route a request only to models that keep no data, or enforce it for a whole key or account. See Gateway controls. - Per-end-user budgets — monthly credit caps per end user of your app, managed under
/api/v1/gateway/end-user-budgets(scopesend_user_budgets:read/end_user_budgets:write). See Gateway controls. - Prompt caching —
prompt_cache_keyon/v1/chat/completionsand/v1/responsespasses through as a cache-routing hint to the models that support it (and is dropped elsewhere);cache_controlblocks on/v1/messagesare accepted so Anthropic SDK code runs unchanged, but explicit breakpoints are not applied yet — caching works from the prompt prefix.usage.prompt_tokens_details.cached_tokensis now always present, and the Usage API reports cache reads and writes.
Payments, evals, contacts and telephony
- Customer payment links — agents can send payment links on calls and WhatsApp that are paid into your own connected Razorpay account. Track them under
/api/v1/payment-requestsand subscribe to thepayment_request.*webhook events. - Evals — an
llm_judgeassertion, a pass-rate gate for CI, and creating an eval case from a real call. See Voice evals. - WhatsApp identities on contacts — contacts carry
whatsapp_bsuid,whatsapp_parent_bsuidandwhatsapp_username, for WhatsApp users who hide their phone number. A BSUID is unique per account like a phone number or email. See Contacts. - TRAI readiness for outbound campaigns — a readiness check for AI outbound calling under the TCCCPR amendment. See Voice campaigns.
Newly documented
- Contacts (
/api/v1/contacts, plus each contact's memory), the handoff queue (/api/v1/handoffs), integrations and sheet automations (/api/v1/integrations,/api/v1/sheet-automations), payment requests, andPOST /api/v1/crm/csv/inspectwere already callable with an API key and now have reference pages. - Webhooks — the delivery body, the
X-CallMissed-Event/X-CallMissed-Deliveryheaders, the retry schedule, and thecall.amd_detectedevent. - Idempotency and Errors — rewritten to match exactly what the API does.
September 2026
Account MCP server — run your account from an AI assistant
- Account MCP server — connect Claude, ChatGPT or any MCP client to
https://api.callmissed.com/api/v1/mcp, sign in with your CallMissed account or an API key, and act on your account through 331 tools: voice agents, calls and campaigns, the inbox, CRM, support desk, WhatsApp, email and more. Every tool is gated by the key's scopes, spending tools are marked, and destructive ones ask first. See Account MCP. - Multilingual voice agents — voice tiers and custom agents accept an auto-detect language, so one agent can answer in the caller's language. See Voice tiers.
New model — GPT-6.1 Sol
gpt-6.1-sol— OpenAI's GPT-6.1 Sol: near-Astra performance for complex coding, computer use and professional work at a lower cost. 1.05M context, 128K output, text + image input, reasoning and tool calling. $2.083 in / $10.42 out per 1M tokens ($0.1042 cached input).- Long prompts — requests with more than 272K input tokens are billed at 2× input and cached-input rates and 1.5× output for the whole request ($4.167 in / $0.2083 cached / $15.63 out per 1M).
reasoning_effort— acceptslow,medium(default),highandxhigh. The model always reasons, sononeandminimalare sent aslow, andmaxis sent asxhigh. Only the default temperature is supported, andmax_tokensmust be at least 3. See API speed.- Paid plans only. See Models.
New models — GPT-6 Sol and GPT-6 Luna
gpt-6-sol— OpenAI's GPT-6 frontier reasoning model for enterprise agents, coding and complex knowledge work; succeedsgpt-5.6-sol. 1.05M context, 128K output, text + image input, reasoning and tool calling. $2.083 in / $10.42 out per 1M tokens ($0.2083 cached input).gpt-6-luna— the efficient GPT-6 model for high-volume, cost-sensitive workloads; succeedsgpt-5.6-luna. Same 1.05M context, vision, reasoning and tools. $0.1042 in / $0.5208 out per 1M tokens ($0.01042 cached input).- Long prompts — requests with more than 272K input tokens are billed at 2× input and cached-input rates and 1.5× output for the whole request.
reasoning_effort— both acceptnone,low,medium,highandxhigh(minimalis sent aslow). When a request includestools, reasoning is set tononeautomatically.max_tokensmust be at least 3. See API speed.- Paid plans only. See Models.
August 2026
Managed Voice Agent — speech-to-speech over one WebSocket
- Managed Voice Agent — a full speech-to-speech pipeline behind a single WebSocket. Stream microphone audio in, get synthesized speech and conversation events back; speech recognition, the language model, text-to-speech, turn-taking and interruption handling are all run and tuned for you. No WebRTC and no client SDK. Two protocols on the same host and the same engine:
wss://api.callmissed.com/v2/voice/agent(CallMissed-native) andwss://api.callmissed.com/v1/agent/converse(Deepgram Voice Agent compatible — an existing Deepgram integration can repoint its URL and work unchanged). Supports in-call tool calling, live model/prompt/voice updates, and sessions up to 2 hours. See Managed Voice Agent. - Voice model catalogue —
GET /api/v1/voice/modelslists every selectable speech-to-text, language and text-to-speech model with a measured latency verdict (eligible,too_slow,unsupported,unmeasured) plus its p50, sample count and budget. Any eligible combination is valid. Models too slow to hold a conversation are not offered — they are listed with the reason, rather than silently disappearing or being offered with a caveat. Verdicts come from real production traffic, not vendor claims, and a model with too few samples readsunmeasuredrather than being assumed fast.
Embeddings, usage API, CRM, support desk and voice-agent operations
- Embeddings —
POST /v1/embeddings, OpenAI-compatible.text-embedding-3-small(1536 dims, $0.02083 / 1M input tokens) andtext-embedding-3-large(3072 dims, $0.1354 / 1M). Batches of up to 128 inputs, optionaldimensionsshortening andbase64output. Both are free-plan callable, taking the free tier to 27 models across five categories. Gated by the key'sllmpermission. See Embeddings. - Usage API —
GET /v1/usage/summary,/logsand/logs.csvreturn your own metering rows for the last 90 days, filterable by service, model, key,session_idandtrace_id. Scopeusage:read. See Usage API. - Gateway tooling — server-side prompt management with versions, labels, presets and free rendering; response cache stats and purge; and bring your own provider key with liveness verification and a write-only secret.
- CRM — companies, notes and tasks, deals and pipelines, custom fields and saved views, search, bulk and CSV, and lead scoring with a unified timeline.
- Support desk — tickets with server-managed lifecycle stamps, SLA policies with business hours and live breach reporting, macros, tags and routing rules with a dry-run evaluator, and CSAT/NPS surveys and a hosted page where customers answer.
- Voice-agent operations — eval suites (up to 50 cases per run, credit-charged), A/B experiments with deterministic assignment, and agent squads with handoff simulation and credit-charged agent drafting.
- WhatsApp — Flows (create, publish, read submissions) and catalog orders.
New models — Cartesia Ink STT
ink-whisper— Cartesia's fastest and most affordable STT at $0.1875 / hour, across 100 languages including Hindi, Urdu and Tamil. Better accuracy than baseline Whisper, and dynamic chunking that cuts hallucination during pauses and silence. Works for both file transcription and voice sessions. See Speech to Text.ink-2— Cartesia's top-ranked STT for voice agents at $0.5625 / hour: 8% WER on AppTek's 14-accent call-centre benchmark, against 10% for Deepgram Flux and 12% for ElevenLabs. Self-detects turns, so no separate turn detector is needed. Two limits: it is English only, and it is voice-session only — the file transcription endpoint returns400and points you toink-whisper. See Speech to Text.
New models — conversational Indic LLM, Saaras V4 STT, Flux TTS
sarvam-105b-conversations— 105B MoE tuned for conversation and voice. 128K context, tool calling, streaming, hybrid thinking. Free-tier, same $0.1563 in / $0.625 out per 1M assarvam-105b. See Indic Models.saaras:v4— Sarvam STT with five output modes (transcribe, translate, verbatim, transliterate, code-mix) across 24 languages. Free-tier at $0.3125 / hour. See Speech to Text.- Deepgram Flux TTS — streaming-first TTS built for voice agents: turn-based synthesis with prosody carried across turns. 36 English voices including
priya(Indian-accented English, the default). English only, no expressive controls. Available only through the managed Voice Agent (tts_engine: "flux"), billed inside the per-minute voice rate. See Voices. - Free tier — now 27 models (11 LLM, 4 STT, 4 TTS, 6 image, 2 embedding).
Model catalog update — retired models
- Retired LLM IDs — the following model IDs are no longer served:
openai/gpt-5.4-pro,openai/gpt-5.4,openai/gpt-5.4-mini,openai/gpt-5.4-nano,anthropic/claude-opus-4.6,anthropic/claude-sonnet-4.6,anthropic/claude-haiku-4.5,x-ai/grok-4.20,qwen/qwen3.5-plus,qwen/qwen3.5-flash,mistralai/mistral-small-2603, and theautoauto-router. - Migration — use the first-party flagships (
gpt-5.6-sol,gpt-5.6-terra,gpt-5.6-luna,gpt-5.5,grok-4.3) or the direct-routed free tier (kimi-k2.6,kimi-k2.7-code,glm-5.2,gpt-oss-120b,mistral-small-3.1). See Models. - Free tier — now 24 models (11 LLM). The
autofree auto-router is retired; pick a free model explicitly. - Endpoints unchanged —
POST /v1/chat/completionsand the Anthropic-compatiblePOST /v1/messagesboth continue to work and accept every current catalog ID.
June 2026
v1.6.0 — WebRTC Voice, Image Generation & Web Search
- WebRTC voice sessions —
POST /v1/voice/sessionsreturns a connection token + URL; CallMissed handles the STT→LLM→TTS pipeline. List, fetch, fetch transcript (json | txt | srt), and end sessions under/v1/voice/sessions. The legacy/ws/voice-agentWebSocket still works for backward compatibility. See Voice Session API. - Image Generation API —
POST /v1/images/generations(OpenAI-compatible). Free models includeflux-2-klein-9b,flux-2-dev,lucid-origin,phoenix-1.0,sdxl-lightning,dreamshaper-8-lcm; paid models includeflux-2-pro,flux-1.1-pro,nano-banana-2, andnano-banana-pro. See Image Generation. - Web Search API —
POST /v1/searchdefaults to Serper web search (Exa, Firecrawl also available); flat 1 credit per query. See Web Search. - Knowledge RAG — vector knowledge sources at
/api/v1/knowledge/sources(ingest text, URL, or PDF; chunked + embedded) with semantic search atPOST /api/v1/knowledge/search.
May 2026
v1.5.0 — First-Party Models, Account Security & WhatsApp Platform
- First-party models — deployments callable by bare ID:
gpt-4o,gpt-4.1,gpt-5-mini,grok-4.3,DeepSeek-V4-Pro,DeepSeek-V4-Flash, plus first-party STT (whisper,gpt-4o-transcribe,gpt-4o-mini-transcribe,gpt-4o-transcribe-diarize) and TTS (gpt-4o-mini-tts). - More STT/TTS —
whisper-large-v3-turbo(99 langs),nova-3(diarization),aura-2-en/aura-2-es, andmelotts— all free-tier. - Kimi K2.6 —
kimi-k2.6added to the direct-routed free tier alongsidekimi-k2.5. - TOTP 2FA & passkeys — two-factor auth (authenticator apps + backup codes) and passkeys for dashboard sign-in. Active sessions can be reviewed and revoked from the dashboard.
- WhatsApp platform — Embedded Signup onboarding, message templates, broadcast campaigns, and delivery analytics under
/api/v1/whatsapp/*. See WhatsApp API. - Billing surfaces — coupon redemption, downloadable PDF invoices, and a credit ledger broken down by transaction type, all in the dashboard.
- Audit log — a sensitive-action audit feed in the dashboard.
April 2026
v1.4.0 — Anthropic API Compatibility & Audio Translation
- Anthropic Messages API — New
POST /v1/messagesendpoint. Use the Anthropic SDK with CallMissed by changing only thebase_url. Full streaming support with Anthropic SSE lifecycle (message_start,content_block_delta,message_stop). - Dual auth headers — Anthropic endpoint accepts both
x-api-keyandAuthorization: Bearerheaders - Model aliasing — A bare model name on the Anthropic endpoint resolves against the CallMissed catalog
- Audio Translation — New
POST /v1/audio/translationsendpoint. Translate audio in 24 languages to English text. OpenAI SDK compatible (client.audio.translations.create()) - Token counting —
POST /v1/messages/count_tokensfor input token estimation - Anthropic rate limit headers —
anthropic-ratelimit-requests-limit,anthropic-ratelimit-requests-remaining, etc.
v1.3.0 — Voice Agent & Ultra-Low-Latency Pipeline
- Voice Agent WebSocket — Real-time STT→LLM→TTS pipeline over
/ws/voice-agent. PCM audio in, streaming MP3 out. LLM and TTS run concurrently for minimum latency. - PCM AudioWorklet capture — Raw PCM s16le at 16kHz, no container overhead
- Streaming MP3 playback — MediaSource API appends and plays chunks as they arrive
- Profile management — Save and update user profile from the dashboard
v1.2.0 — Security, Google OAuth & Plan Enforcement
- Sign in with Google — Google sign-in for the dashboard. Auto-creates the organisation and user, and links to an existing account by email.
- OTP Authentication — Email-based OTP for passwordless login and password reset
- Plan limit enforcement — Server-side usage caps per plan tier (free/starter/pro/enterprise). API returns
429 quota_exceededwhen limits reached. Usage headers (X-RateLimit-*,X-Usage-Warning) on every response. - Per-API-key rate limiting — a requests-per-minute limit on every key (today set by plan; see Rate limits)
- Model catalog update — OpenAI gpt-5.4 family, Anthropic Claude 4.6, Google Gemini 3.1, xAI Grok 4.20, Qwen 3.5, Mistral Small
- Knowledge Base file upload — Upload PDF, DOCX, TXT files (max 20 MB) with auto text extraction
- Bot deployment verification — Verify WhatsApp/Twilio channel connectivity from the dashboard
- Settings verification — Verify WhatsApp, Twilio, and Indic LLM API connectivity
v1.1.0 — Platform Playground
- Playground rebuild — LLM (streaming + non-streaming), STT (file upload + mic), TTS (37 voices across 11 Indian languages), Voice Agent demo
v1.0.0 — Initial Release
- Chat Completion API — OpenAI-compatible endpoint with streaming, tool calls, and function calling
- Speech to Text —
saaras:v3with 22 Indic language support - Text to Speech —
bulbul:v3(37 voices across 11 Indian languages) - WhatsApp Bot — Full WhatsApp Business API integration
- Voice Calling — Twilio-based inbound voice with WebSocket streaming
- Multi-tenant — Complete tenant isolation with role-based access
- API Keys — Scoped API keys with usage tracking
- Webhook Delivery — Outbound webhooks with retry and HMAC signing
- Analytics Dashboard — Real-time conversation and usage analytics
- Model catalog — LLM, STT, TTS and image models from one OpenAI-compatible endpoint