| PRICING |
Fireworks AI |
Ultramarine 1 Flash (US) input $0.225 → $0.15/1M (-33%) · output $0.75 → $0.5/1M (-33%) · cached input $0.045 → $0.03/1M (-33%) |
10d ago |
| PRICING |
Fireworks AI |
DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) input $2.4/1M (new) · output $9.6/1M (new) · cached input $0.048/1M (new) |
10d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
11d ago |
| DEPRECATION |
Azure |
gpt-5-mini (2025-08-07) shutdown 2027-02-09 → 2027-07-13 · gpt-5.1 (2025-11-13) shutdown 2027-05-15 → 2027-07-13 |
14d ago |
| DOCS |
Anthropic |
Claude Fable 5.x RPM 1K → 4K · Claude Opus 5.5 RPM 1K → 4K · Claude Sonnet 5.5 RPM 1K → 4K +1 |
14d ago |
| DEPRECATION |
Mistral AI |
mistral-medium-3-5 shutdown 2027-04-30 · replacement Mistral Large 4 · voxtral-mini-tts-2603 shutdown 2027-04-30 +7 |
14d ago |
| DOCS |
DeepSeek Rate Limits |
DeepSeek Rate Limits changed: Search / Fetch API is now available, powered by our in-house search engine and supporting web search and fetch. Click |
15d ago |
| BASELINE |
DeepSeek |
DeepSeek API Pricing: tracking began · 2 models |
15d ago |
| DOCS |
OpenAI |
As an alternative to creating a region-specific project, you can select regional processing for an individual request by using the prefixed… |
16d ago |
| DOCS |
OpenAI |
`/v1/decisions` · No · 30 days · None, see below for exceptions · Yes, see below for limitations · Yes, see below for limitations |
16d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Qwen3.8 Flash Next FP8 |
18d ago |
| DOCS |
OpenAI |
The legacy Completions examples below use `gpt-3.5-turbo-instruct`, which has a [scheduled shutdown date of September 28… |
18d ago |
| DOCS |
OpenAI |
Fast mode supports EU data residency for GPT-6.1 Sol, GPT-6.1 Terra, and GPT-6 Luna. Fast mode is not available with EU data residency for GPT-6 Astra or GPT-6 Sol. GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, and GPT-6 Luna support EU data residency with Standard, Flex, and Batch… |
18d ago |
| DEPRECATION |
Azure |
gpt-realtime-2 (2026-05-06) shutdown 2027-01-20 · replacement gpt-realtime-2.1 |
21d ago |
| DOCS |
OpenAI |
Except as noted below, the Responses API has a 30 day Application State retention period by default, or when the `store` parameter is set to `true`. In those cases, response data will be stored for at least 30 days. * When Zero Data Retention is enabled for an organization… |
21d ago |
| DOCS |
OpenAI |
Image generation is Zero Data Retention compatible when using `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, `gpt-image-2`, `gpt-image-1.5`, and `gpt-image-1-mini`. |
21d ago |
| DOCS |
OpenAI |
OpenAI uses sub-processors to provide its services. For requests sent to `us.api.openai.com` or `eu.api.openai.com`, OpenAI uses Cloudflare Regional Services so that TLS termination and HTTPS decryption occur within the selected processing region. |
21d ago |
| DOCS |
OpenAI |
OpenAI uses sub-processors to provide its services. For requests sent to `us.api.openai.com`, `eu.api.openai.com`, `au.api.openai.com`, `in.api.openai.com`, or `jp.api.openai.com`, OpenAI uses Cloudflare Regional Services so that TLS termination and HTTPS decryption occur within… |
21d ago |
| DOCS |
Fireworks AI |
MiniMax M3.1 Flash $0.15/M Input • $0.6/M Output • 1048576 Context … |
22d ago |
| PRICING |
Together AI |
MiniMax M3.1 Flash input $0.15/1M (new) · output $0.6/1M (new) · cached input $0.015/1M (new) |
22d ago |
| DOCS |
Anthropic |
Our Usage Policy (also referred to as our “Acceptable Use Policy” or “AUP”) applies to anyone who submits inputs to Anthropic’s products or services, all of whom we refer to as “users.” This includes individuals using our apps (such as Claude.ai and Claude Code), developers and… |
23d ago |
| DOCS |
Anthropic |
The API enforces service-configured limits at the organization level, but you may also set user-configurable limits for your… |
23d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Kalshi-tuned Muse Glimmer 30B |
24d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Rune 26B-A4B |
24d ago |
| DOCS |
Anthropic |
Welcome to Anthropic! Before accessing our Services, please read these Commercial Terms of Service. |
24d ago |
| DOCS |
Anthropic |
Anthropic is an AI safety and research company working to build reliable, interpretable, and steerable AI systems. |
24d ago |
| PRICING |
Together AI |
DeepSeek V4.1 Flash 1017 input $0.3/1M (new) · output $1.2/1M (new) · cached input $0.006/1M (new) |
26d ago |
| DOCS |
Fireworks AI |
DeepSeek V4.1 Flash 1017 $0.3/M Input • $1.2/M Output • 1048576 Context … |
27d ago |
| PRICING |
Together AI |
Reflection Beam input $0.4/1M (new) · output $1.2/1M (new) · cached input $0.04/1M (new) |
28d ago |
| PRICING |
Together AI |
Muse Spark Open (Free for limited time) input $0/1M (new) · output $0/1M (new) |
28d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Reflection Beam-1.0-501B-A23B |
28d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Beam-1.0-501B-A23B |
29d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Muse Spark Open 816B-A42B NVFP4 |
29d ago |
| DOCS |
Fireworks AI |
[New Muse Spark Open $1.25/M Input • $4.25/M Output • 1048576 Context … |
29d ago |
| PRICING |
Together AI |
Muse Spark Open input $1.25/1M (new) · output $4.25/1M (new) · cached input $0.15/1M (new) |
29d ago |
| DOCS |
Fireworks AI |
[ New NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 1048576 Context … |
29d ago |
| PRICING |
Together AI |
NVIDIA Nemotron 3.5 Super VL input $0.15/1M (new) · output $0.5/1M (new) · cached input $0.02/1M (new) |
30d ago |
| DEPRECATION |
Azure |
gpt-chat-latest (2026-05-05) shutdown 2026-08-05 → 2026-11-17 · gpt-chat-latest (2026-05-28) shutdown 2026-08-28 → 2026-12-08 · gpt-chat-latest (2026-06-24) shutdown 2026-09-24 → 2026-11-17 +2 |
30d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed: grok-voice-3.0 |
30d ago |
| DOCS |
Anthropic |
describing which rate limit was exceeded, along with a `retry-after` header indicating how long to wait. |
31d ago |
| DEPRECATION |
OpenAI |
GPT-4o (gpt-4o-2024-08-06, gpt-4o-2024-11-20) shutdown 2027-01-14 · replacement gpt-6-luna · GPT-4o mini (gpt-4o-mini-2024-07-18) shutdown 2027-01-14 +5 |
31d ago |
| PRICING |
Together AI |
Kimi K3 cached input $0.27 → $0.3/1M (+11%) |
31d ago |
| DOCS |
Fireworks AI |
Fireworks AI Models changed: Drex v2.0 |
32d ago |
| PRICING |
Together AI |
Kimi K3 input $2.7 → $3/1M (+11%) · output $13.5 → $15/1M (+11%) |
33d ago |
| DEPRECATION |
Azure |
gpt-4.1-nano (2025-04-14) shutdown 2026-10-14 → 2027-04-14 |
36d ago |
| DOCS |
Anthropic |
Anthropic Rate Limits changed: Limits are set at the organization level. You can see your organization's tier and current limits on the Rate limits |
37d ago |
| DOCS |
Anthropic |
Anthropic Rate Limits changed: Claude Haiku 3.5 (retired, except on Google Cloud ) |
37d ago |
| DOCS |
Anthropic |
Claude Haiku 5.5 · 1,000 · 2,000,000 · 400,000 · Claude Haiku 5.5 · 5,000 · 5,000,000 · 1,000,000 · Claude Haiku 5.5 · 10,000 · … |
37d ago |
| DOCS |
Anthropic |
_3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5. |
38d ago |
| DEPRECATION |
Google |
gemini-3.1-flash-image shutdown 2026-10-29 · replacement gemini-nano-banana-2.1 · gemini-2.5-flash-image replacement gemini-3.1-flash-image-preview → gemini-nano-banana-2.1 +6 |
38d ago |
| PRICING |
Together AI |
Kimi K3 input $3 → $2.7/1M (-10%) · output $15 → $13.5/1M (-10%) · cached input $0.3 → $0.27/1M (-10%) +2 |
39d ago |
| DOCS |
Anthropic |
Anthropic Rate Limits changed |
39d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
43d ago |
| DEPRECATION |
Google |
gemini-2.5-computer-use-preview-10-2025 shutdown 2026-07-28 · replacement gemini-3.8-flash |
44d ago |
| DEPRECATION |
Anthropic |
claude-sonnet-4-5-20250929 shutdown 2026-11-30 · replacement claude-sonnet-5-5 |
44d ago |
| DOCS |
Anthropic |
The error type is `rate_limit_error`, the same as for a rate limit, but the response has no `retry-after` header. |
45d ago |
| DEPRECATION |
Mistral AI |
zai-glm-5-2 shutdown 2026-10-31 · replacement Z.ai GLM 5.3 · labs-leanstral-1-5 shutdown 2026-09-30 +2 |
45d ago |
| DEPRECATION |
Google |
veo-3.1-lite-generate-preview shutdown 2026-10-22 · replacement gemini-omni-1.1-flash · veo-3.1-generate-preview shutdown 2026-10-22 +3 |
45d ago |
| DOCS |
Anthropic |
Claude Sonnet 5.5 · 1,000 · 2,000,000 · 400,000 · - _3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across… |
46d ago |
| DEPRECATION |
Azure |
gpt-4.1 · 2025-04-14 · Legacy · 2027-04-14 · — · gpt-4.1-mini · 2025-04-14 · Legacy · 2027-04-14 · — · gpt-4.1-nano · … |
51d ago |
| DOCS |
Azure |
gpt-realtime-2 · 2026-05-06 · Preview · 2026-08-31 · — · gpt-realtime-2 · 2026-05-06 · Preview · — · gpt-realtime-2.1 · - * Last… |
51d ago |
| DOCS |
Google |
`gemini-3.8-flash-tts` · September 22, 2026 · No shutdown date announced · `gemini-3.8-flash-lite-tts` · September 22, 2026 · No … |
51d ago |
| PRICING |
Together AI |
Qwen3.8 Flash input $0.15 → $0.09/1M (-40%) · output $0.47 → $0.28/1M (-40%) · Qwen3.7-Max input $2.5 → $1.5/1M (-40%) +2 |
52d ago |
| DOCS |
OpenAI |
enables OpenAI to perform automated safety monitoring while preserving Zero Data Retention protections. Endpoint and feature limitations listed on this page still apply. Customers using Zero Data Retention with Private Safety Processing must configure customer-controlled storage… |
52d ago |
| DOCS |
OpenAI |
For customers approved for Zero Data Retention or Modified Abuse Monitoring, we reserve the right to make models ineligible for Zero Data Retention or Modified Abuse Monitoring for specific customers, as notified in advance to the impacted customers in writing. In this instance… |
52d ago |
| DOCS |
OpenAI |
The table below indicates when application state is stored for each endpoint. Zero Data Retention eligible endpoints do not retain any customer content for application state, subject to the limitations below. Zero Data Retention ineligible endpoints or capabilities may retain… |
52d ago |
| DOCS |
Anthropic |
Claude Opus 5.5 · 1,000 · 2,000,000 · 400,000 · - _2 Opus rate limit is a total limit that applies to combined traffic across Claude… |
52d ago |
| DOCS |
Anthropic |
claude-opus-5-5 · Active · N/A · Not sooner than September 22, 2027 |
52d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
53d ago |
| PRICING |
xAI |
Grok 4.7 input $2/1M (new) · output $6/1M (new) |
53d ago |
| BASELINE |
DeepSeek |
DeepSeek API Pricing: tracking began · 2 models |
56d ago |
| DOCS |
Azure |
gpt-realtime-2.1 · 2026-07-07 · Preview · 2027-06-25 · — · gpt-realtime-2.1-mini · 2026-07-07 · Preview · 2027-06-25 · — · gpt… |
56d ago |
| DEPRECATION |
Anthropic |
claude-mythos-5-1 · Active · N/A · Not sooner than September 1, 2027 · claude-mythos-5 · Active · N/A · Not sooner than June 9… |
56d ago |
| BASELINE |
DeepSeek |
DeepSeek API Pricing: tracking began · 2 models |
56d ago |
| DOCS |
Azure |
gpt-4.1-nano · 2025-04-14 · Legacy · 2026-10-14 · — · gpt-4.1-nano · 2025-04-14 · Legacy · 2027-04-14 · — |
56d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
57d ago |
| BASELINE |
OpenAI |
OpenAI API Pricing: tracking began · 18 models |
57d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
57d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
57d ago |
| DOCS |
xAI Rate Limits |
xAI Rate Limits changed |
57d ago |
| BASELINE |
Fireworks AI |
Fireworks AI Pricing: tracking began · 21 models |
58d ago |