DeepSeek V4 Flash (DeepSeek-V4-Flash-0731): official fast chat and code model with thinking and non-thinking modes, 1M context, and up to 384K output.

deepseek/deepseek-v4-flashchatdeepseek

Retail priceinput $8.8e-07 · cached input $2.8e-08 · output $2.64e-06

→

DeepSeek V4 ProAvailable

DeepSeek V4 Pro (DeepSeek-V4-Pro-0813): official premium reasoning and coding model with thinking and non-thinking modes, 1M context, and up to 384K output.

deepseek/deepseek-v4-prochatdeepseek

Retail priceinput $2.64e-06 · cached input $8.8e-08 · output $7.92e-06

→

Gemini 3 Flash PreviewAvailable

Use gemini-3-flash-preview to power AI agent conversations and automation tasks. Ideal for Claude Code integration, rapid response generation, and intelligent workflow automation.

google/gemini-3-flash-previewchatgoogle

Retail priceinput $1e-06 · output $6e-06 · cached input $1e-07

→

Gemini 3.1 Pro PreviewAvailable

Gemini 3.1 Pro preview — flagship reasoning + multimodal. /v1beta/models/gemini-3.1-pro-preview:generateContent.

google/gemini-3.1-pro-previewchatgoogle

Retail priceinput $4e-06 · output $2.4e-05 · cached input $1e-06

→

Gemini 3.5 FlashAvailable

Gemini 3.5 Flash compatibility chat model

google/gemini-3.5-flashchatgoogle

Retail priceinput $1e-06 · output $6e-06

→

Gemini 3.6 FlashAvailable

Gemini 3.6 Flash compatibility chat model

google/gemini-3.6-flashchatgoogle

Retail priceinput $1e-06 · output $6e-06

→

GLM 4.5 AirAvailable

GLM-4.5-Air by Z.ai — lightweight, cost-efficient chat model. OpenAI-compatible: pass model=glm/glm-4.5-air to /v1/chat/completions.

glm/glm-4.5-airchatglm

Retail priceinput $4e-07 · output $2.2e-06 · cached input $6e-08

→

GLM 4.5VAvailable

GLM-4.5V by Z.ai — multimodal vision+language model for image understanding. OpenAI-compatible: pass model=glm/glm-4.5v to /v1/chat/completions with image_url content.

glm/glm-4.5vchatglm

Retail priceinput $1.2e-06 · output $3.6e-06 · cached input $2.2e-07

→

GLM 4.7Available

GLM-4.7 by Z.ai — enhanced programming model, great price/performance. OpenAI-compatible: pass model=glm/glm-4.7 to /v1/chat/completions.

glm/glm-4.7chatglm

Retail priceinput $1.2e-06 · output $4.4e-06 · cached input $2.2e-07

→

GLM 5Available

GLM-5 by Z.ai — strong coding and multi-step reasoning at a lower price tier. OpenAI-compatible: pass model=glm/glm-5 to /v1/chat/completions.

glm/glm-5chatglm

Retail priceinput $2e-06 · output $6.4e-06 · cached input $4e-07

→

GLM 5 TurboAvailable

GLM-5-Turbo by Z.ai — speed-optimized GLM-5 for high-throughput agentic workloads. OpenAI-compatible: pass model=glm/glm-5-turbo to /v1/chat/completions.

glm/glm-5-turbochatglm

Retail priceinput $2.4e-06 · output $8e-06 · cached input $4.8e-07

→

GLM 5.1Available

GLM-5.1 by Z.ai — flagship chat model with strong Chinese + English coverage, function calling, and fine-grained token streaming. OpenAI-compatible: pass model=glm/glm-5.1 to /v1/chat/completions.

glm/glm-5.1chatglm

Retail priceinput $2.8e-06 · output $8.8e-06 · cached input $5.2e-07

→

GLM 5.2Available

GLM-5.2 by Z.ai — latest flagship chat model, 1M-token context, strong coding + long-horizon agentic reasoning. OpenAI-compatible: pass model=glm/glm-5.2 to /v1/chat/completions.

glm/glm-5.2chatglm

Retail priceinput $2.8e-06 · output $8.8e-06 · cached input $5.2e-07

→

gpt-4.1Available

Openai-r openai/gpt-4.1 - chat model

openai/gpt-4.1chatopenai

Retail priceinput $4e-06 · output $1.6e-05 · cached input $1e-06

→

gpt-4.1-miniAvailable

Openai-r openai/gpt-4.1-mini - chat model

openai/gpt-4.1-minichatopenai

Retail priceinput $8e-07 · output $3.2e-06 · cached input $2e-07