Providers with tracked quotes
75 inference providers currently have endpoint quotes for 269 tracked models, all observed through OpenRouter, plus DeepSeek, Z.AI, Groq, Xiaomi direct quotes with recorded source reviews. This is the list of who is priced here, not a directory of every AI vendor.
Covered
- 842 active endpoint quotes (842 including unavailable ones kept for reference).
- Paired input/output rates, cache read/write rates where published, quantization, context and declared parameters.
- Direct quotes priced in: CNY, USD.
- Prices as of 2026-11-22 · tracked since 2026-09-29 · 148 checks so far.
Not covered yet
- Official direct price pages for most providers; the direct quotes below are the current exceptions.
- Regional pricing beyond the direct quotes, context-length tiers and volume discounts.
- Embeddings, audio, image and video billing; only text generation is compared.
- Free-tier allowances, data-use terms and concurrency limits.
- Measured latency, success rate and quality; price is the only ranked dimension.
Endpoint providers via OpenRouter
| Provider | Models | Endpoints (active / total) | Cache rates published | Latest price change | Actions |
|---|---|---|---|---|---|
| AionLabs | 6 | 6 / 6 | 5 of 6 | None since 2026-09-29 | Compare |
| AkashML | 1 | 1 / 1 | 1 of 1 | Compare | |
| Alibaba | 22 | 29 / 29 | 22 of 29 | Compare | |
| Amazon Bedrock | 20 | 28 / 28 | 5 of 28 | None since 2026-09-29 | Compare |
| Ambient | 2 | 2 / 2 | 2 of 2 | Compare | |
| Ant Digital | 1 | 1 / 1 | 0 of 1 | None since 2026-11-15 | Compare |
| Azure | 11 | 11 / 11 | 4 of 11 | None since 2026-09-29 | Compare |
| Baidu | 7 | 7 / 7 | 6 of 7 | Compare | |
| BaseTen | 13 | 23 / 23 | 23 of 23 | Compare | |
| Cerebras | 2 | 2 / 2 | 2 of 2 | None since 2026-09-29 | Compare |
| Chutes | 7 | 7 / 7 | 7 of 7 | Compare | |
| Cloudflare | 10 | 10 / 10 | 6 of 10 | Compare | |
| Cohere | 11 | 11 / 11 | 7 of 11 | Compare | |
| CoreWeave | 21 | 21 / 21 | 21 of 21 | Compare | |
| Crusoe | 7 | 7 / 7 | 7 of 7 | Compare | |
| Darkbloom | 12 | 12 / 12 | 12 of 12 | Compare | |
| Decart | 1 | 1 / 1 | 1 of 1 | Compare | |
| DeepInfra | 81 | 134 / 134 | 56 of 134 | Compare | |
| DekaLLM | 1 | 1 / 1 | 0 of 1 | None since 2026-09-29 | Compare |
| DigitalOcean | 16 | 16 / 16 | 16 of 16 | Compare | |
| Doubleword | 1 | 1 / 1 | 1 of 1 | None since 2026-11-20 | Compare |
| Featherless | 2 | 2 / 2 | 2 of 2 | Compare | |
| Fireworks | 13 | 21 / 21 | 21 of 21 | Compare | |
| Friendli | 3 | 3 / 3 | 2 of 3 | None since 2026-09-29 | Compare |
| 5 | 5 / 5 | 1 of 5 | None since 2026-09-29 | Compare | |
| Google AI Studio | 3 | 3 / 3 | 0 of 3 | None since 2026-09-29 | Compare |
| Groq | 4 | 4 / 4 | 4 of 4 | None since 2026-09-29 | Compare |
| Inceptron | 6 | 6 / 6 | 6 of 6 | Compare | |
| Inferact vLLM | 1 | 1 / 1 | 1 of 1 | Compare | |
| InferenceNet | 9 | 22 / 22 | 22 of 22 | Compare | |
| Io Net | 4 | 4 / 4 | 4 of 4 | Compare | |
| Ionstream | 3 | 3 / 3 | 3 of 3 | Compare | |
| KT | 7 | 7 / 7 | 7 of 7 | Compare | |
| Liquid | 3 | 3 / 3 | 2 of 3 | None since 2026-11-21 | Compare |
| Makora | 9 | 9 / 9 | 9 of 9 | Compare | |
| Mancer 2 | 10 | 10 / 10 | 10 of 10 | Compare | |
| Mistral | 23 | 36 / 36 | 31 of 36 | Compare | |
| Modal | 10 | 10 / 10 | 10 of 10 | None since 2026-09-29 | Compare |
| ModelRun | 7 | 7 / 7 | 7 of 7 | Compare | |
| Moonshot AI | 4 | 6 / 6 | 6 of 6 | None since 2026-10-24 | Compare |
| Morph | 14 | 15 / 15 | 11 of 15 | Compare | |
| Near AI | 4 | 4 / 4 | 4 of 4 | Compare | |
| Nebius | 20 | 20 / 20 | 19 of 20 | Compare | |
| Nex AGI | 2 | 2 / 2 | 2 of 2 | None since 2026-09-29 | Compare |
| NextBit | 5 | 5 / 5 | 3 of 5 | Compare | |
| Novita | 19 | 19 / 19 | 12 of 19 | Compare | |
| Nvidia | 7 | 7 / 7 | 0 of 7 | None since 2026-09-29 | Compare |
| OpenAI | 8 | 8 / 8 | 5 of 8 | None since 2026-09-29 | Compare |
| OpenInference | 3 | 3 / 3 | 3 of 3 | Compare | |
| Parasail | 39 | 46 / 46 | 39 of 46 | Compare | |
| Particle AI | 4 | 7 / 7 | 6 of 7 | Compare | |
| Pearl Research | 1 | 1 / 1 | 1 of 1 | None since 2026-11-19 | Compare |
| Perceptron | 2 | 2 / 2 | 0 of 2 | None since 2026-09-29 | Compare |
| Perplexity | 2 | 2 / 2 | 0 of 2 | None since 2026-09-29 | Compare |
| PrimaLabs | 4 | 4 / 4 | 4 of 4 | Compare | |
| PrimeIntellect | 14 | 14 / 14 | 12 of 14 | Compare | |
| Recursive | 1 | 1 / 1 | 0 of 1 | None since 2026-10-22 | Compare |
| Reka | 6 | 6 / 6 | 4 of 6 | Compare | |
| Relace | 13 | 13 / 13 | 11 of 13 | Compare | |
| River | 5 | 5 / 5 | 5 of 5 | Compare | |
| Sail Research | 10 | 15 / 15 | 15 of 15 | Compare | |
| SambaNova | 1 | 1 / 1 | 0 of 1 | None since 2026-09-29 | Compare |
| Seed | 1 | 1 / 1 | 0 of 1 | None since 2026-09-29 | Compare |
| SiliconFlow | 37 | 37 / 37 | 22 of 37 | Compare | |
| StepFun | 1 | 1 / 1 | 1 of 1 | None since 2026-09-29 | Compare |
| StreamLake | 1 | 1 / 1 | 0 of 1 | None since 2026-09-29 | Compare |
| Tencent | 3 | 3 / 3 | 0 of 3 | None since 2026-09-29 | Compare |
| Tenstorrent | 5 | 5 / 5 | 5 of 5 | Compare | |
| Together | 24 | 24 / 24 | 22 of 24 | Compare | |
| Unbiased | 3 | 3 / 3 | 3 of 3 | None since 2026-10-01 | Compare |
| Venice | 30 | 32 / 32 | 26 of 32 | Compare | |
| VoyageAI by MongoDB | 5 | 5 / 5 | 0 of 5 | None since 2026-11-04 | Compare |
| Wafer | 10 | 19 / 19 | 19 of 19 | Compare | |
| Xiaomi | 3 | 3 / 3 | 3 of 3 | None since 2026-09-29 | Compare |
| Z.AI | 15 | 15 / 15 | 15 of 15 | Compare |
Direct quotes with recorded source reviews
Read from official price pages in the currency the provider bills, requiring review within 7 days or earlier source/decision expiry. They are the seed of direct-provider coverage, not its full extent.
DeepSeek · DeepSeek-V4.1-Flash-1017
Standard · CNY · Region not specified · checked 2026-11-20
CN¥2.00 in / CN¥8.00 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4.1-Flash-1017; API identifier: deepseek-flash. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: peak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: CNY. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in peak window. Cache miss. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Includes thinking tokens. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Cache hit. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4.1-Flash-1017
Off-peak · CNY · Region not specified · checked 2026-11-20
CN¥1.00 in / CN¥4.00 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4.1-Flash-1017; API identifier: deepseek-flash. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: offpeak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: CNY. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in offpeak window. Cache miss. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Includes thinking tokens. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Cache hit. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4-Pro-0813
Standard · CNY · Region not specified · checked 2026-11-20
CN¥9.00 in / CN¥27.00 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4-Pro-0813; API identifier: deepseek-v4-pro. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: peak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: CNY. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in peak window. Cache miss. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Includes thinking tokens. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Cache hit. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4-Pro-0813
Off-peak · CNY · Region not specified · checked 2026-11-20
CN¥4.50 in / CN¥13.50 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4-Pro-0813; API identifier: deepseek-v4-pro. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: offpeak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: CNY. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in offpeak window. Cache miss. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Includes thinking tokens. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Cache hit. Peak: Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4.1-Flash-1017
Standard · USD · Region not specified · checked 2026-11-20
$0.30 in / $1.20 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4.1-Flash-1017; API identifier: deepseek-flash. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: peak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: USD. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in peak window. Cache miss. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Includes thinking tokens. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Cache hit. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4.1-Flash-1017
Off-peak · USD · Region not specified · checked 2026-11-20
$0.15 in / $0.60 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4.1-Flash-1017; API identifier: deepseek-flash. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: offpeak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: USD. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in offpeak window. Cache miss. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Includes thinking tokens. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Cache hit. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4-Pro-0813
Standard · USD · Region not specified · checked 2026-11-20
$1.32 in / $3.96 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4-Pro-0813; API identifier: deepseek-v4-pro. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: peak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: USD. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in peak window. Cache miss. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Includes thinking tokens. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in peak window. Cache hit. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
DeepSeek · DeepSeek-V4-Pro-0813
Off-peak · USD · Region not specified · checked 2026-11-20
$0.66 in / $1.98 out
Official pricingBilling conditions
Official current model version: DeepSeek-V4-Pro-0813; API identifier: deepseek-v4-pro. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays. Selected billing window: offpeak. Cache-hit input uses the cache-read rate; cache-miss input uses the input rate. Thinking tokens are billed as output. Context: 1M tokens; documented maximum output: 384K. Standalone Search and Fetch APIs are billed per successful request. Since November 18, 2026 at 12:00 Beijing time, model-triggered server-side search and fetch carry no separate tool fee; returned content is billed as model token usage. Token reference subtotals exclude independent API calls. Billing currency: USD. Deployment region and account availability are not established by this price page; region is unspecified, not inferred from currency or document language. Supports documented JSON output and tool calls, with thinking enabled by default and thinking/reasoning_effort controls. Control documentation: https://api-docs.deepseek.com/guides/thinking_mode/; internal evidence SHA-256: 5ab9a7b03778a41ea37046b88936a3066fcfe9085d6b7436b5fc0ec371b08a88. Output quality and strict schema adherence are not established.
Applies in offpeak window. Cache miss. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Includes thinking tokens. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Applies in offpeak window. Cache hit. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Off-peak: all other times, including weekends and Chinese public holidays.
Z.AI · GLM-5.3-Flash
Standard · CNY · Region not specified · checked 2026-11-20
CN¥0.80 in / CN¥2.80 out
Official pricingBilling conditions
Standard token rates. Cache storage listed as limited-time free; no permanent zero rate recorded.
Z.AI · GLM-5.3-Flash
Standard · USD · Region not specified · checked 2026-11-20
$0.15 in / $0.50 out
Official pricingBilling conditions
Standard token rates. Cache storage listed as limited-time free; no permanent zero rate recorded.
Groq · Whisper Large V3 Turbo
Standard · USD · Region not specified · checked 2026-11-18
duration: 0.04 USD / hour
Minimum charge per file: 10 seconds
Official pricingBilling conditions
Standard synchronous transcription, production listing; USD 0.04 per audio hour; minimum billed duration 10 seconds per request; minimum accepted file 0.01 seconds. Account/file-size limits, taxes, custom contracts, Batch and other services excluded; no quality or access guarantee. Currency proof: c5b3de857f41a23325c2dd256737dc5d1ba93af12c6b387975b079acecd9def0 (full_document_email_links_v1); raw response e3d388b5f00f79e2c4a50e62829af8f3f006c567151d20856bef1160ebca55ba. Source model listing is production; not tested account availability. Unit-specific known charges only, not a complete bill.
Groq · Whisper Large V3
Standard · USD · Region not specified · checked 2026-11-18
duration: 0.111 USD / hour
Minimum charge per file: 10 seconds
Official pricingBilling conditions
Standard synchronous transcription, production listing; USD 0.111 per audio hour; minimum billed duration 10 seconds per request; minimum accepted file 0.01 seconds. Account/file-size limits, taxes, custom contracts, Batch and other services excluded; no quality or access guarantee. Currency proof: c5b3de857f41a23325c2dd256737dc5d1ba93af12c6b387975b079acecd9def0 (full_document_email_links_v1); raw response e3d388b5f00f79e2c4a50e62829af8f3f006c567151d20856bef1160ebca55ba. Source model listing is production; not tested account availability. Unit-specific known charges only, not a complete bill.
Xiaomi · MiMo-V2.6-Flash
Standard · USD · Region not specified · checked 2026-11-20
$0.14 in / $0.28 out
Official pricingBilling conditions
Pay-as-you-go token rates for the stated currency. Deployment region and account eligibility unspecified.
Xiaomi · MiMo-V2.6-Flash
Standard · CNY · Region not specified · checked 2026-11-20
CN¥1.00 in / CN¥2.00 out
Official pricingBilling conditions
Pay-as-you-go token rates for the stated currency. Deployment region and account eligibility unspecified.
Model developers and other AI companies are listed separately in the vendor directory; being listed there does not mean a vendor’s prices are tracked here.