Granite 4.2 8B API

Model details

Context window

131K tokens

Max output

118K tokens

Input

Text

Output

Text

Capabilities

Reasoning, Tool calling, Streaming, JSON output

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Granite 4.2 8B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Granite 4.2 8B

Granite 4.2 8B answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "granite-4.2-8b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "granite-4.2-8b",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "granite-4.2-8b",
  "input": "Hello"
}'

Use Granite 4.2 8B in your tools

Every coding agent below has a setup guide. Set the model to granite-4.2-8b.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

Alternatives to Granite 4.2 8B

• Qwen3.5 9BQwen3.5 9B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Alibaba
• GLM-4 32B (0414-128k)GLM-4 32B (0414-128k) for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Z.ai
• Ministral 3BMinistral 3B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Mistral

Questions about this model

How much does the Granite 4.2 8B API cost?

Granite 4.2 8B costs $0.06 per 1M input tokens and $0.25 per 1M output tokens on Inferray, and cached input is $0.015 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Granite 4.2 8B?

No. You add credit and pay Granite 4.2 8B's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Granite 4.2 8B included in Token Plans?

No. Granite 4.2 8B is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Granite 4.2 8B in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to granite-4.2-8b. The same key works in Codex, opencode, Cline, and other agents.

Does Granite 4.2 8B support tool calling and vision?

Granite 4.2 8B supports tool calling, reasoning, JSON output and streaming on Inferray. It does not take image input.

Is it the real Granite 4.2 8B?

Yes. A request for granite-4.2-8b is answered by Granite 4.2 8B from Ibm, billed at its published list price. Inferray never substitutes a different or smaller model.