diff --git a/api-reference/authentication.mdx b/api-reference/authentication.mdx
index 54b324a..e55337f 100644
--- a/api-reference/authentication.mdx
+++ b/api-reference/authentication.mdx
@@ -69,7 +69,7 @@ To verify your network can reach the Pioneer API during integration, send a requ
 curl -X POST https://api.pioneer.ai/v1/messages \
   -H "X-API-Key: pio_sk_test" \
   -H "Content-Type: application/json" \
-  -d '{"model":"claude-haiku-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
+  -d '{"model":"claude-haiku-4-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
 
 # Expected: {"detail":"Invalid API key format. API keys must start with 'pio_sk_'. Please check your X-API-Key header."}
 # A 401 with this body = integration is wired correctly. Swap in a real key to get completions.
diff --git a/cn/api-reference/authentication.mdx b/cn/api-reference/authentication.mdx
index cbc98b8..ad8ca6f 100644
--- a/cn/api-reference/authentication.mdx
+++ b/cn/api-reference/authentication.mdx
@@ -69,7 +69,7 @@ curl -X DELETE https://api.pioneer.ai/delete-api-key \
 curl -X POST https://api.pioneer.ai/v1/messages \
   -H "X-API-Key: pio_sk_test" \
   -H "Content-Type: application/json" \
-  -d '{"model":"claude-haiku-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
+  -d '{"model":"claude-haiku-4-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
 
 # Expected: {"detail":"Invalid API key format. API keys must start with 'pio_sk_'. Please check your X-API-Key header."}
 # A 401 with this body = integration is wired correctly. Swap in a real key to get completions.
diff --git a/cn/concepts/models.mdx b/cn/concepts/models.mdx
index 5e019ee..c8cb93f 100644
--- a/cn/concepts/models.mdx
+++ b/cn/concepts/models.mdx
@@ -54,7 +54,9 @@ GLiNER 模型执行命名实体识别和结构化提取。大多数 GLiNER 基
 | --- | --- |
 | `claude-opus-5` | Claude Opus 5 |
 | `claude-sonnet-5` | Claude Sonnet 5 |
-| `claude-haiku-5` | Claude Haiku 5 |
+| `claude-opus-5-fast` | Claude Opus 5 (Fast) |
+| `claude-fable-5` | Claude Fable 5 |
+| `claude-haiku-4-5` | Claude Haiku 4.5 |
 
 ### OpenAI
 
@@ -76,7 +78,13 @@ GLiNER 模型执行命名实体识别和结构化提取。大多数 GLiNER 基
 | Model ID | 标签 |
 | --- | --- |
 | `zai-org/GLM-5.2` | GLM 5.2 |
-| `zai-org/GLM-5.2-Fast` | GLM 5.2 Fast |
+
+### Moonshot AI
+
+| Model ID | 标签 |
+| --- | --- |
+| `moonshotai/Kimi-K3` | Kimi K3 |
+| `moonshotai/Kimi-K3-Fast` | Kimi K3 Fast |
 
 <Note>
   这些系列之外的模型不是受支持的推理目标。集成前请使用 `GET /base-models` 查询实时目录和生命周期状态。
diff --git a/concepts/models.mdx b/concepts/models.mdx
index acafb7f..c427da2 100644
--- a/concepts/models.mdx
+++ b/concepts/models.mdx
@@ -41,47 +41,73 @@ live source of truth for availability.
 
 ## Decoder models — serverless inference
 
-These are the supported pre-deployed inference families. Query
-`GET /base-models?supports_inference=true` for live availability, context
-limits, and pricing.
+These are the supported pre-deployed inference families. Rates are USD per 1M tokens.
+Query `GET /base-models?supports_inference=true` for live availability, context limits,
+and pricing — it is the source of truth if it ever disagrees with this page.
+
+<Note>
+  **Cached input** is what a prompt-cache hit costs (see [prompt caching](#prompt-caching)).
+  Where it equals the input rate, that route does not price cache reads separately.
+  A dash means the rate is not published for that model — rollout-gated models return
+  their rates only to workspaces with the rollout enabled.
+</Note>
 
 ### Nemotron 3.5 Lightning
 
-| Model ID | Label |
-| --- | --- |
-| `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` | Nemotron 3.5 Lightning 30B-A3B |
-| `fastino/Fastino-Nemotron-3.5-Lightning-Finance` | Fastino Nemotron 3.5 Lightning Finance |
-| `fastino/Fastino-Nemotron-3.5-Lightning-Healthcare` | Fastino Nemotron 3.5 Lightning Healthcare |
+| Model ID | Label | Input | Output | Cached input | Context |
+| --- | --- | --- | --- | --- | --- |
+| `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` | Nemotron 3.5 Lightning 30B-A3B | \$0.50 | \$0.50 | \$0.50 | 8,192 |
+| `fastino/Fastino-Nemotron-3.5-Lightning-Finance` | Fastino Nemotron 3.5 Lightning Finance | \$0.50 | \$0.50 | \$0.50 | 8,192 |
+| `fastino/Fastino-Nemotron-3.5-Lightning-Healthcare` | Fastino Nemotron 3.5 Lightning Healthcare | \$0.50 | \$0.50 | \$0.50 | 8,192 |
 
 ### Anthropic
 
-| Model ID | Label |
-| --- | --- |
-| `claude-opus-5` | Claude Opus 5 |
-| `claude-sonnet-5` | Claude Sonnet 5 |
-| `claude-haiku-5` | Claude Haiku 5 |
+| Model ID | Label | Input | Output | Cached input | Context |
+| --- | --- | --- | --- | --- | --- |
+| `claude-opus-5` | Claude Opus 5 | \$5.00 | \$25.00 | \$0.50 | 1,000,000 |
+| `claude-sonnet-5` | Claude Sonnet 5 | \$2.00 | \$10.00 | \$0.20 | 1,000,000 |
+| `claude-opus-5-fast` | Claude Opus 5 (Fast) | \$10.00 | \$50.00 | \$1.00 | 1,000,000 |
+| `claude-fable-5` | Claude Fable 5 | \$11.00 | \$55.00 | \$1.10 | 1,000,000 |
+| `claude-haiku-4-5` | Claude Haiku 4.5 | \$1.00 | \$5.00 | \$0.10 | 200,000 |
 
 ### OpenAI
 
-| Model ID | Label |
-| --- | --- |
-| `gpt-5.5` | GPT-5.5 |
-| `gpt-5.6-luna` | GPT-5.6 Luna |
-| `gpt-5.6-terra` | GPT-5.6 Terra |
-| `gpt-5.6-sol` | GPT-5.6 Sol |
+| Model ID | Label | Input | Output | Cached input | Context |
+| --- | --- | --- | --- | --- | --- |
+| `gpt-5.5` | GPT-5.5 | \$5.00 | \$30.00 | \$0.50 | 1,000,000 |
+| `gpt-5.6-luna` | GPT-5.6 Luna | \$1.00 | \$6.00 | \$0.10 | 1,050,000 |
+| `gpt-5.6-terra` | GPT-5.6 Terra | \$2.50 | \$15.00 | \$0.25 | 1,050,000 |
+| `gpt-5.6-sol` | GPT-5.6 Sol | \$5.00 | \$30.00 | \$0.50 | 1,050,000 |
+
+<Warning>
+  **GPT-5 models bill a long-context tier.** Requests whose prompt exceeds
+  **272,000 tokens** are charged at roughly double the rates above — GPT-5.5 and
+  GPT-5.6 Sol go to \$10.00 / \$45.00 / \$1.00, GPT-5.6 Terra to \$5.00 / \$22.50 /
+  \$0.50, and GPT-5.6 Luna to \$2.00 / \$9.00 / \$0.20. The rest of this page's
+  rates are the standard tier.
+</Warning>
 
 ### DeepSeek
 
-| Model ID | Label |
-| --- | --- |
-| `deepseek-ai/DeepSeek-V4-Flash` | DeepSeek V4 Flash |
+| Model ID | Label | Input | Output | Cached input | Context |
+| --- | --- | --- | --- | --- | --- |
+| `deepseek-ai/DeepSeek-V4-Flash` | DeepSeek V4 Flash | \$0.14 | \$0.28 | \$0.028 | 1,000,000 |
+
+The dated pin `deepseek-ai/DeepSeek-V4-Flash-0731` remains a working alias for this
+entry — both resolve to the same 0731 checkpoint upstream.
 
 ### Z.ai
 
-| Model ID | Label |
-| --- | --- |
-| `zai-org/GLM-5.2` | GLM 5.2 |
-| `zai-org/GLM-5.2-Fast` | GLM 5.2 Fast |
+| Model ID | Label | Input | Output | Cached input | Context |
+| --- | --- | --- | --- | --- | --- |
+| `zai-org/GLM-5.2` | GLM 5.2 | \$1.40 | \$4.40 | \$0.14 | 1,040,000 |
+
+### Moonshot AI
+
+| Model ID | Label | Input | Output | Cached input | Context |
+| --- | --- | --- | --- | --- | --- |
+| `moonshotai/Kimi-K3` | Kimi K3 | \$3.00 | \$15.00 | \$0.30 | 1,000,000 |
+| `moonshotai/Kimi-K3-Fast` | Kimi K3 Fast | \$4.50 | \$22.50 | \$0.45 | 1,000,000 |
 
 <Note>
   Models outside these families are not supported inference targets. Use
diff --git a/concepts/router.mdx b/concepts/router.mdx
index 18fc693..26cfae6 100644
--- a/concepts/router.mdx
+++ b/concepts/router.mdx
@@ -68,7 +68,7 @@ The router selects from this pool. Use the **Candidate Models** setting to restr
 | Nemotron 3.5 Lightning | NVIDIA / Fastino |
 | DeepSeek V4 Flash | DeepSeek |
 | GLM 5.2 | ZhipuAI |
-| Claude Haiku 5 | Anthropic |
+| Claude Haiku 4.5 | Anthropic |
 | Claude Sonnet 5 | Anthropic |
 | Claude Opus 5 | Anthropic |
 | GPT-5.5 | OpenAI |
diff --git a/de/api-reference/authentication.mdx b/de/api-reference/authentication.mdx
index f473dc6..8015fa5 100644
--- a/de/api-reference/authentication.mdx
+++ b/de/api-reference/authentication.mdx
@@ -69,7 +69,7 @@ Um während der Integration zu prüfen, ob Ihr Netzwerk die Pioneer API erreiche
 curl -X POST https://api.pioneer.ai/v1/messages \
   -H "X-API-Key: pio_sk_test" \
   -H "Content-Type: application/json" \
-  -d '{"model":"claude-haiku-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
+  -d '{"model":"claude-haiku-4-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
 
 # Expected: {"detail":"Invalid API key format. API keys must start with 'pio_sk_'. Please check your X-API-Key header."}
 # A 401 with this body = integration is wired correctly. Swap in a real key to get completions.
diff --git a/de/concepts/models.mdx b/de/concepts/models.mdx
index 349ae6a..e90b053 100644
--- a/de/concepts/models.mdx
+++ b/de/concepts/models.mdx
@@ -54,7 +54,9 @@ Dies sind die unterstützten vorab bereitgestellten Inferenzfamilien. Fragen Sie
 | --- | --- |
 | `claude-opus-5` | Claude Opus 5 |
 | `claude-sonnet-5` | Claude Sonnet 5 |
-| `claude-haiku-5` | Claude Haiku 5 |
+| `claude-opus-5-fast` | Claude Opus 5 (Fast) |
+| `claude-fable-5` | Claude Fable 5 |
+| `claude-haiku-4-5` | Claude Haiku 4.5 |
 
 ### OpenAI
 
@@ -76,7 +78,13 @@ Dies sind die unterstützten vorab bereitgestellten Inferenzfamilien. Fragen Sie
 | Model ID | Label |
 | --- | --- |
 | `zai-org/GLM-5.2` | GLM 5.2 |
-| `zai-org/GLM-5.2-Fast` | GLM 5.2 Fast |
+
+### Moonshot AI
+
+| Model ID | Label |
+| --- | --- |
+| `moonshotai/Kimi-K3` | Kimi K3 |
+| `moonshotai/Kimi-K3-Fast` | Kimi K3 Fast |
 
 <Note>
   Modelle außerhalb dieser Familien werden nicht als Inferenzziele unterstützt. Verwenden Sie vor der Integration `GET /base-models` für den Live-Katalog und den Lifecycle-Status.
diff --git a/es/api-reference/authentication.mdx b/es/api-reference/authentication.mdx
index 5e75531..8c4b16c 100644
--- a/es/api-reference/authentication.mdx
+++ b/es/api-reference/authentication.mdx
@@ -69,7 +69,7 @@ Para verificar que tu red puede alcanzar la API de Pioneer durante la integraci
 curl -X POST https://api.pioneer.ai/v1/messages \
   -H "X-API-Key: pio_sk_test" \
   -H "Content-Type: application/json" \
-  -d '{"model":"claude-haiku-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
+  -d '{"model":"claude-haiku-4-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
 
 # Expected: {"detail":"Invalid API key format. API keys must start with 'pio_sk_'. Please check your X-API-Key header."}
 # A 401 with this body = integration is wired correctly. Swap in a real key to get completions.
diff --git a/es/concepts/models.mdx b/es/concepts/models.mdx
index aff5422..f587871 100644
--- a/es/concepts/models.mdx
+++ b/es/concepts/models.mdx
@@ -54,7 +54,9 @@ Estas son las familias de inferencia predesplegadas admitidas. Consulta `GET /ba
 | --- | --- |
 | `claude-opus-5` | Claude Opus 5 |
 | `claude-sonnet-5` | Claude Sonnet 5 |
-| `claude-haiku-5` | Claude Haiku 5 |
+| `claude-opus-5-fast` | Claude Opus 5 (Fast) |
+| `claude-fable-5` | Claude Fable 5 |
+| `claude-haiku-4-5` | Claude Haiku 4.5 |
 
 ### OpenAI
 
@@ -76,7 +78,13 @@ Estas son las familias de inferencia predesplegadas admitidas. Consulta `GET /ba
 | Model ID | Etiqueta |
 | --- | --- |
 | `zai-org/GLM-5.2` | GLM 5.2 |
-| `zai-org/GLM-5.2-Fast` | GLM 5.2 Fast |
+
+### Moonshot AI
+
+| Model ID | Etiqueta |
+| --- | --- |
+| `moonshotai/Kimi-K3` | Kimi K3 |
+| `moonshotai/Kimi-K3-Fast` | Kimi K3 Fast |
 
 <Note>
   Los modelos fuera de estas familias no se admiten como destinos de inferencia. Usa `GET /base-models` para consultar el catálogo en vivo y el estado del ciclo de vida antes de integrarlos.
diff --git a/faq.mdx b/faq.mdx
index 802f674..999b3e0 100644
--- a/faq.mdx
+++ b/faq.mdx
@@ -27,7 +27,7 @@ Find answers to the most common questions about Pioneer below. If you don't see
   </Accordion>
 
   <Accordion title="Which decoder models can I call?">
-    Pioneer supports Nemotron 3.5 Lightning, DeepSeek V4 Flash, GLM 5.2, Claude Opus/Sonnet/Haiku 5, and the GPT-5.5 and GPT-5.6 family through one unified API.
+    Pioneer supports Nemotron 3.5 Lightning, DeepSeek V4 Flash, GLM 5.2, Claude Opus 5, Sonnet 5 and Haiku 4.5, and the GPT-5.5 and GPT-5.6 family through one unified API.
 
     ```bash
     curl -X POST https://api.pioneer.ai/inference \
diff --git a/fr/api-reference/authentication.mdx b/fr/api-reference/authentication.mdx
index 82eee2e..e2888ba 100644
--- a/fr/api-reference/authentication.mdx
+++ b/fr/api-reference/authentication.mdx
@@ -69,7 +69,7 @@ Pour vérifier que votre réseau peut atteindre l'API Pioneer pendant l'intégra
 curl -X POST https://api.pioneer.ai/v1/messages \
   -H "X-API-Key: pio_sk_test" \
   -H "Content-Type: application/json" \
-  -d '{"model":"claude-haiku-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
+  -d '{"model":"claude-haiku-4-5","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
 
 # Expected: {"detail":"Invalid API key format. API keys must start with 'pio_sk_'. Please check your X-API-Key header."}
 # A 401 with this body = integration is wired correctly. Swap in a real key to get completions.
diff --git a/fr/concepts/models.mdx b/fr/concepts/models.mdx
index a71fdf4..8a3fa40 100644
--- a/fr/concepts/models.mdx
+++ b/fr/concepts/models.mdx
@@ -54,7 +54,9 @@ Voici les familles décodeurs pré-déployées prises en charge pour l'inférenc
 | --- | --- |
 | `claude-opus-5` | Claude Opus 5 |
 | `claude-sonnet-5` | Claude Sonnet 5 |
-| `claude-haiku-5` | Claude Haiku 5 |
+| `claude-opus-5-fast` | Claude Opus 5 (Fast) |
+| `claude-fable-5` | Claude Fable 5 |
+| `claude-haiku-4-5` | Claude Haiku 4.5 |
 
 ### OpenAI
 
@@ -76,7 +78,13 @@ Voici les familles décodeurs pré-déployées prises en charge pour l'inférenc
 | Model ID | Libellé |
 | --- | --- |
 | `zai-org/GLM-5.2` | GLM 5.2 |
-| `zai-org/GLM-5.2-Fast` | GLM 5.2 Fast |
+
+### Moonshot AI
+
+| Model ID | Libellé |
+| --- | --- |
+| `moonshotai/Kimi-K3` | Kimi K3 |
+| `moonshotai/Kimi-K3-Fast` | Kimi K3 Fast |
 
 <Note>
   Les modèles qui ne font pas partie de ces familles ne sont pas des cibles d'inférence prises en charge. Utilisez `GET /base-models` pour consulter le catalogue et l'état du cycle de vie en direct avant toute intégration.
diff --git a/guides/fine-tune-llm.mdx b/guides/fine-tune-llm.mdx
index f2b1a61..eea061c 100644
--- a/guides/fine-tune-llm.mdx
+++ b/guides/fine-tune-llm.mdx
@@ -247,7 +247,7 @@ the supported inference families:
 | `zai-org/GLM-5.2` | GLM 5.2 | See live catalog |
 | `claude-opus-5` | Claude Opus 5 | See live catalog |
 | `claude-sonnet-5` | Claude Sonnet 5 | See live catalog |
-| `claude-haiku-5` | Claude Haiku 5 | See live catalog |
+| `claude-haiku-4-5` | Claude Haiku 4.5 | See live catalog |
 | `gpt-5.5` | GPT-5.5 | See live catalog |
 | `gpt-5.6-terra` | GPT-5.6 Terra | See live catalog |
 
diff --git a/introduction.mdx b/introduction.mdx
index c64bc73..4ee6648 100644
--- a/introduction.mdx
+++ b/introduction.mdx
@@ -64,7 +64,7 @@ Pioneer supports two classes of models: encoder models for structured extraction
 
 **Proprietary models (inference only)**
 
-- **Claude Opus 5 / Claude Sonnet 5 / Claude Haiku 5** — Anthropic models available through Pioneer's Anthropic-compatible endpoint.
+- **Claude Opus 5 / Claude Sonnet 5 / Claude Haiku 4.5** — Anthropic models available through Pioneer's Anthropic-compatible endpoint.
 - **GPT-5.5 and GPT-5.6** — OpenAI models available through Pioneer's OpenAI-compatible endpoint.
 
 To see all available base models, call `GET /base-models`. You can filter by task type or inference support.