Published API listings with native prices and dated evidence. Check the official source for current availability and account eligibility.
DeepInfra input and output pricesUSD per 1M tokens · headline rates · log scale
Input
Output
DeepInfra input and output prices
Category
Item
USD per 1M tokens
gpt-oss-120b
Input
$0.037
gpt-oss-120b
Output
$0.17
DeepSeek V4 Flash 0731
Input
$0.06
DeepSeek V4 Flash 0731
Output
$0.18
Ling 3.0 Flash
Input
$0.06
Ling 3.0 Flash
Output
$0.18
NVIDIA Nemotron 3.5 Lightning
Input
$0.06
NVIDIA Nemotron 3.5 Lightning
Output
$0.16
Llama 3.3 70B Instruct Turbo
Input
$0.10
Llama 3.3 70B Instruct Turbo
Output
$0.32
Qwen3.6 35B A3B
Input
$0.10
Qwen3.6 35B A3B
Output
$0.95
MiMo V2.6 Flash
Input
$0.14
MiMo V2.6 Flash
Output
$0.28
MiniMax M3
Input
$0.28
MiniMax M3
Output
$1.10
MiMo V2.6 Pro
Input
$0.43
MiMo V2.6 Pro
Output
$0.87
NVIDIA Nemotron 3 Ultra 550B A55B
Input
$0.50
NVIDIA Nemotron 3 Ultra 550B A55B
Output
$2.20
Kimi K2.6
Input
$0.75
Kimi K2.6
Output
$3.50
DeepSeek V4 Pro 0813
Input
$1.30
DeepSeek V4 Pro 0813
Output
$2.60
Kimi K3
Input
$2.85
Kimi K3
Output
$14.25
Headline USD token rates per 1M; other currencies and units remain native. Original rates are below. Unknown means no unambiguous headline; inspect all rates and conditions below.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "deepseek-ai/DeepSeek-V4-Flash-0731" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "deepseek-ai/DeepSeek-V4-Flash-0731" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"deepseek-ai/DeepSeek-V4-Flash-0731" has "max_tokens":1048576. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-0731, raw SHA-256 8891dd9dfe798909dc94cce6369b5245f72961ea47a10cea259943dbb9b0b08a, fetched 2026-10-14T01:52:00Z) shows 1,048,576 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
DeepSeek V4 Pro 0813
Service ID: deepseek-ai/DeepSeek-V4-Pro-0813 · Context window: 1,048,576 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "deepseek-ai/DeepSeek-V4-Pro-0813" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "deepseek-ai/DeepSeek-V4-Pro-0813" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"deepseek-ai/DeepSeek-V4-Pro-0813" has "max_tokens":1048576. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro-0813, raw SHA-256 ce5baed2e6cac4bfb508916c3287444c62718471f10ea0be9d9bd1276d528b2d, fetched 2026-10-14T01:52:00Z) shows 1,048,576 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
gpt-oss-120b
Service ID: openai/gpt-oss-120b · Context window: 131,072 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "openai/gpt-oss-120b" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "openai/gpt-oss-120b" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"openai/gpt-oss-120b" has "max_tokens":131072. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/openai/gpt-oss-120b, raw SHA-256 10843ab091753711bc42e87d6e7bce966440e4b6b7a646f294012cb301e29745, fetched 2026-10-14T01:52:02Z) shows 131,072 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Kimi K2.6
Service ID: moonshotai/Kimi-K2.6 · Context window: 262,144 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "moonshotai/Kimi-K2.6" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "moonshotai/Kimi-K2.6" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"moonshotai/Kimi-K2.6" has "max_tokens":262144. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/moonshotai/Kimi-K2.6, raw SHA-256 a86cec63090a933e07101fcd6f02a5f31ca4bcad87ebc5ecd7c48d0b84ec8c8f, fetched 2026-10-14T01:52:01Z) shows 262,144 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Kimi K3
Service ID: moonshotai/Kimi-K3 · Context window: 1,048,576 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "moonshotai/Kimi-K3" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "moonshotai/Kimi-K3" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"moonshotai/Kimi-K3" has "max_tokens":1048576. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/moonshotai/Kimi-K3, raw SHA-256 78dc58227ebd3015c84ef9766335fe51c092c8432b7cfbb49ab5fef8e3d88db2, fetched 2026-10-14T01:52:00Z) shows 1,048,576 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Ling 3.0 Flash
Service ID: inclusionAI/Ling-3.0-flash · Context window: 131,072 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "inclusionAI/Ling-3.0-flash" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "inclusionAI/Ling-3.0-flash" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"inclusionAI/Ling-3.0-flash" has "max_tokens":131072. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/inclusionAI/Ling-3.0-flash, raw SHA-256 77633ffc9e2de43d82c3f19ceffd6ea119ea2fb934c953244350f7e9ad011285, fetched 2026-10-14T01:52:04Z) shows 131,072 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Llama 3.3 70B Instruct Turbo
Service ID: meta-llama/Llama-3.3-70B-Instruct-Turbo · Context window: 131,072 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "meta-llama/Llama-3.3-70B-Instruct-Turbo" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "meta-llama/Llama-3.3-70B-Instruct-Turbo" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"meta-llama/Llama-3.3-70B-Instruct-Turbo" has "max_tokens":131072. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo, raw SHA-256 d4acada2c682ce6e468e9c909ea94aa5948d4a2efda4ae58f5a0502fa7820d5d, fetched 2026-10-14T01:52:03Z) shows 131,072 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
MiMo V2.6 Flash
Service ID: XiaomiMiMo/MiMo-V2.6-Flash · Context window: 1,048,576 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "XiaomiMiMo/MiMo-V2.6-Flash" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "XiaomiMiMo/MiMo-V2.6-Flash" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"XiaomiMiMo/MiMo-V2.6-Flash" has "max_tokens":1048576. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/XiaomiMiMo/MiMo-V2.6-Flash, raw SHA-256 0877cf630657fb60590ee8a947d28ef3127a17707edc811ae0958227271dc574, fetched 2026-10-14T01:52:02Z) shows 1,048,576 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
MiMo V2.6 Pro
Service ID: XiaomiMiMo/MiMo-V2.6-Pro · Context window: 1,048,576 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "XiaomiMiMo/MiMo-V2.6-Pro" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "XiaomiMiMo/MiMo-V2.6-Pro" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"XiaomiMiMo/MiMo-V2.6-Pro" has "max_tokens":1048576. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/XiaomiMiMo/MiMo-V2.6-Pro, raw SHA-256 328c814a6ef4478b485d9d5233b7015a8cb0c5ea4dd8c224a48c5475e7954b5e, fetched 2026-10-14T01:52:02Z) shows 1,048,576 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
MiniMax M3
Service ID: MiniMaxAI/MiniMax-M3 · Context window: 524,288 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "MiniMaxAI/MiniMax-M3" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "MiniMaxAI/MiniMax-M3" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"MiniMaxAI/MiniMax-M3" has "max_tokens":524288. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/MiniMaxAI/MiniMax-M3, raw SHA-256 43998f9cc41a2b8250bd0b10377091a5ec7f1877f640b74dfd9e496b4ad6155a, fetched 2026-10-14T01:52:01Z) shows 524,288 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
NVIDIA Nemotron 3 Ultra 550B A55B
Service ID: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B · Context window: 262,144 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B" has "max_tokens":262144. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, raw SHA-256 fd4e68dbcfc5a8fe62a6c01d9180f53c5613a0f1255c5037f20edc80e0c5188a, fetched 2026-10-14T01:52:03Z) shows 262,144 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
NVIDIA Nemotron 3.5 Lightning
Service ID: nvidia/NVIDIA-Nemotron-3.5-Lightning · Context window: 262,144 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "nvidia/NVIDIA-Nemotron-3.5-Lightning" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "nvidia/NVIDIA-Nemotron-3.5-Lightning" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"nvidia/NVIDIA-Nemotron-3.5-Lightning" has "max_tokens":262144. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning, raw SHA-256 ee6141d688f7121750f566afbaa6fe0a6bcb957bf0b58d5ac55d6ae5f667a03b, fetched 2026-10-14T01:52:03Z) shows 262,144 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Qwen3.6 35B A3B
Service ID: Qwen/Qwen3.6-35B-A3B · Context window: 262,144 tokens · Listing status: active
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "Qwen/Qwen3.6-35B-A3B" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
Model "Qwen/Qwen3.6-35B-A3B" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.
Output tokens (cents_per_output_token).
Developer: Unknown / not verified · API seller: DeepInfra
Checkpoint: Unknown / not verified · Lineage: Unknown / not verified
Raw SHA-256: bc2430a05d8c87b4886bf56dd44dda63f039d8fe4cb9aef475e7ba8994780bb7; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 2f004322a828d0826740a204576d682540381093346f0f0dfee228686d50a930; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 241a1acbecb07feda39c570e80dc69cf45c1ab72e1d32c68b36f01d1272f0783; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Raw SHA-256: 8c270c2250fb2f4065d9c4b0506582ceb7cdf0be7a7337421de06b558a982855; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"Qwen/Qwen3.6-35B-A3B" has "max_tokens":262144. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/Qwen/Qwen3.6-35B-A3B, raw SHA-256 69b97b65f7fe2f57acdef8448927377f458e1495f0a283c71080c5b03569b76f, fetched 2026-10-14T01:52:04Z) shows 262,144 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
Specifications only: no pricing, availability, capability or release-date assertion.
Raw SHA-256: b2974c6049c9cdc30a349ed1276bd850d42ba2db9473bcf203243ce1108406aa; collector deepinfra-models-json-1.
Hosted listing and pricing observation only: thirteen reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI.
About capability scores (Epoch AI)
Capability scores: Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource], epoch.ai/benchmarks. Accessed 2026-10-14. Licensed CC BY 4.0; values here are rounded to one decimal place and grouped into bands.
The Epoch Capabilities Index (ECI) combines many benchmarks on a scale where Claude 3.5 Sonnet is 130 and GPT-5 is 150. Bands, on the displayed one-decimal score: Frontier 160+, Strong 150–159.9, Capable 140–149.9, Entry below 140. Each score has a 90% range; a range that crosses a band boundary is flagged. Models are not ranked: neighbouring scores often overlap.
A benchmark is not your workload. Epoch's scores mostly reflect runs at the highest reasoning effort, which use more output tokens than default settings. Scores are dated and can shift between Epoch releases. A score belongs to the developer's model; a host listing shows the same model's score, but hosts may serve different versions or quantizations.
How headline rates are chosen
Headline rates use the directory's shared rule: the rate a buyer meets by default, chosen by billing, tier and context dimensions and never by price. Context caps, the bracket starting at zero and short-context variants are labeled; unverified availability is flagged and is not a service guarantee. Batch, off-peak and other variants remain in the details; ambiguous headlines stay unknown.
No currency conversion is performed. Missing cache prices are unknown, not zero. Equal units do not establish equivalent models or service conditions. See the methodology and source register.