feat(providers): add Jalapeno Cloud (#4880)

Co-authored-by: jychen_magik123 <jychen@magikcompute.ai>
2026-08-18 00:44:14 +08:00
parent 22f6b3b4cd
commit a6d20f0b62
21 changed files with 304 additions and 0 deletions
@@ -0,0 +1,24 @@
+name = "Qwen3 VL 235B A22B Instruct"
+description = "Qwen vision-language instruct model for visual reasoning, documents, and agent tasks"
+family = "qwen"
+release_date = "2025-09-23"
+last_updated = "2025-09-23"
+attachment = true
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2025-03-31"
+open_weights = true
+
+[limit]
+context = 131_072
+output = 32_768
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
+
+[[weights]]
+label = "Hugging Face"
+url = "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"
@@ -0,0 +1,24 @@
+name = "Qwen3 VL 235B A22B Thinking"
+description = "Qwen vision-language thinking model for visual reasoning, documents, and agent tasks"
+family = "qwen"
+release_date = "2025-09-23"
+last_updated = "2025-09-23"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2025-03-31"
+open_weights = true
+
+[limit]
+context = 131_072
+output = 32_768
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
+
+[[weights]]
+label = "Hugging Face"
+url = "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Thinking"
@@ -0,0 +1,8 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor">
+  <path d="M15.5 4.52C16.03 4.48 16.97 4.63 17.15 5C17.33 5.37 16.37 6.21 16.68 6.9C16.99 7.59 18.55 8.68 19.15 9.5C19.75 10.32 20.54 11.23 20.6 12.2C20.66 13.17 20.23 14.69 19.55 15.8C18.87 16.91 17.61 18.42 16.2 19.4C14.79 20.38 12.18 21.74 10.4 22.15C8.62 22.56 6.15 22.6 4.6 22.05C3.05 21.5 0.32 19.43 0.35 18.55C0.38 17.67 3.52 17.33 4.8 16.35C6.08 15.37 7.67 13.62 8.7 12.2C9.73 10.78 10.73 8.22 11.5 7.15C12.27 6.08 13.08 5.65 13.7 5.25C14.32 4.85 14.97 4.56 15.5 4.52Z"/>
+  <rect x="21.6" y="1.6" width="2.4" height="2.2"/>
+  <rect x="18.6" y="3" width="2" height="2"/>
+  <rect x="21.2" y="8" width="2" height="2"/>
+  <rect x="22.2" y="5" width="1.8" height="1.8"/>
+  <rect x="19" y="5.8" width="1.8" height="1.8"/>
+</svg>
@@ -0,0 +1,15 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=DeepSeek-V4-Flash (2026-08-17)
+base_model = "deepseek/deepseek-v4-flash"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.14
+output = 0.28
+
+[limit]
+context = 1_048_576
@@ -0,0 +1,15 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=DeepSeek-V4-Pro (2026-08-17)
+base_model = "deepseek/deepseek-v4-pro"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 1.60
+output = 3.38
+
+[limit]
+context = 1_048_576
@@ -0,0 +1,15 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=GLM-5.1 (2026-08-17)
+base_model = "zhipuai/glm-5.1"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 1.38
+output = 4.40
+
+[limit]
+context = 202_752
@@ -0,0 +1,15 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=GLM-5.2 (2026-08-17)
+base_model = "zhipuai/glm-5.2"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 1.40
+output = 4.40
+
+[limit]
+context = 1_048_576
@@ -0,0 +1,16 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Hy3 (2026-08-17)
+base_model = "tencent/hy3"
+reasoning_options = [{ type = "toggle" }]
+structured_output = true
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.14
+output = 0.58
+
+[limit]
+context = 202_752
@@ -0,0 +1,15 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Kimi-K2.5 (2026-08-17)
+base_model = "moonshotai/kimi-k2.5"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.60
+output = 3.00
+
+[limit]
+output = 180_224
@@ -0,0 +1,16 @@
+# Always-on thinking on this host (dedicated coding ID; Moonshot first-party
+# also publishes no caller control). Interleaved as reasoning_content.
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Kimi-K2.7-Code (2026-08-17)
+base_model = "moonshotai/kimi-k2.7-code"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.95
+output = 4.00
+
+[limit]
+context = 271_360
@@ -0,0 +1,12 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Kimi-K3 (2026-08-17)
+base_model = "moonshotai/kimi-k3"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 3.00
+output = 15.00
@@ -0,0 +1,16 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=MiniMax-M3 (2026-08-17)
+base_model = "minimax/MiniMax-M3"
+reasoning_options = [{ type = "toggle" }]
+structured_output = true
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.30
+output = 1.20
+
+[limit]
+context = 524_288
@@ -0,0 +1,11 @@
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3-Next-80B-A3B-Instruct (2026-08-17)
+base_model = "alibaba/qwen3-next-80b-a3b-instruct"
+structured_output = true
+
+[cost]
+input = 0.15
+output = 1.50
+
+[limit]
+context = 129_024
@@ -0,0 +1,14 @@
+# Always-on thinking on this host: dedicated *-Thinking ID still emits
+# reasoning_content when chat_template_kwargs.thinking=false (live-checked 2026-08-17).
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3-Next-80B-A3B-Thinking (2026-08-17)
+base_model = "alibaba/qwen3-next-80b-a3b-thinking"
+reasoning_options = []
+structured_output = true
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.15
+output = 1.50
@@ -0,0 +1,10 @@
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3-VL-235B-A22B-Instruct (2026-08-17)
+base_model = "alibaba/qwen3-vl-235b-a22b-instruct"
+
+[cost]
+input = 0.30
+output = 1.50
+
+[limit]
+context = 129_024
@@ -0,0 +1,12 @@
+# Always-on thinking on this host (dedicated *-Thinking ID).
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3-VL-235B-A22B-Thinking (2026-08-17)
+base_model = "alibaba/qwen3-vl-235b-a22b-thinking"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.98
+output = 3.95
@@ -0,0 +1,12 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3.5-122B-A10B (2026-08-17)
+base_model = "alibaba/qwen3.5-122b-a10b"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.40
+output = 3.20
@@ -0,0 +1,12 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3.5-27B (2026-08-17)
+base_model = "alibaba/qwen3.5-27b"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.30
+output = 2.40
@@ -0,0 +1,12 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3.5-35B-A3B (2026-08-17)
+base_model = "alibaba/qwen3.5-35b-a3b"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.25
+output = 2.00
@@ -0,0 +1,12 @@
+# Toggle: chat_template_kwargs.thinking true|false
+# Pricing: Jalapeno Cloud USD per million tokens (marketplace / plugin catalog)
+# Limits: GET https://api.jalapeno-cloud.ai/v1/models id=Qwen3.5-397B-A17B (2026-08-17)
+base_model = "alibaba/qwen3.5-397b-a17b"
+reasoning_options = [{ type = "toggle" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.60
+output = 3.60
@@ -0,0 +1,18 @@
+name = "Jalapeno Cloud"
+env = ["JALAPENO_API_KEY"]
+npm = "@ai-sdk/openai-compatible"
+# Reasoning HTTP format (accessed 2026-08-17):
+# Audited POST https://api.jalapeno-cloud.ai/v1/chat/completions.
+# Public quick-start (https://www.jalapeno-cloud.ai/) documents
+# chat_template_kwargs.thinking = true|false as the thinking toggle.
+# Live check: thinking=true emits reasoning_content / reasoning_tokens;
+# thinking=false drops reasoning_tokens on GLM-5.1. Dedicated *-Thinking
+# model IDs still reason when thinking=false (always-on).
+# Interleaved reasoning is returned as reasoning_content.
+# Do not invent reasoning_effort / thinking_budget unless this host is
+# shown to honor those fields.
+# Sources:
+# https://www.jalapeno-cloud.ai/
+# https://api.jalapeno-cloud.ai/v1/models
+api = "https://api.jalapeno-cloud.ai/v1"
+doc = "https://www.jalapeno-cloud.ai/docs/"