GPT-6.1 Terra vs Claude Haiku 5.5
Claude Haiku 5.5 is the lower-priced of the two on Router One at base-tier rates (GPT-6.1 Terra: request input ≤ 272,000 tokens; Claude Haiku 5.5: request input ≤ 100,000 tokens) — about 70% less on a 1M-input + 1M-output mix. Both carry a 1.05M context window. GPT-6.1 Terra answers on /v1/chat/completions and /v1/responses (Codex CLI); Claude Haiku 5.5 on /v1/chat/completions and /v1/messages (Claude Code).
GPT-6.1 Terra and Claude Haiku 5.5 compared on current per-token rates, context window, and capabilities — both callable through one OpenAI-compatible endpoint with per-request cost traces.
GPT-6.1 Terra vs Claude Haiku 5.5: rates, context window, and capabilities
| Spec | GPT-6.1 Terra | Claude Haiku 5.5 |
|---|---|---|
| Input / 1M tokens | $0.20 | $0.06 |
| Output / 1M tokens | $1.00 | $0.30 |
| Cached input / 1M tokens | $0.01 | $0.006 |
| Context window | 1.05M | 1.05M |
| Capabilities | Chat, Streaming, Tool calling, Vision | Chat, Streaming, Tool calling, Vision |
| Subscription plans | Not in any plan — wallet | Not in any plan — wallet |
| Detail page | GPT-6.1 Terra | Claude Haiku 5.5 |
GPT-6.1 Terra: request input ≤ 272,000 tokens: Input $0.20 / 1M tokens, Output $1.00 / 1M tokens, Cache write $0.25 / 1M tokens, Cached input $0.01 / 1M tokens; request input > 272,000 tokens: Input $0.40 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.02 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.
Claude Haiku 5.5: request input ≤ 100,000 tokens: Input $0.06 / 1M tokens, Output $0.30 / 1M tokens, Cache write $0.075 / 1M tokens, Cached input $0.006 / 1M tokens; request input > 100,000 tokens: Input $0.30 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.375 / 1M tokens, Cached input $0.03 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.
What does 1M tokens cost on GPT-6.1 Terra vs Claude Haiku 5.5?
Base-tier rates: For a workload of 1M input plus 1M output tokens at current rates: GPT-6.1 Terra comes to $1.20, Claude Haiku 5.5 comes to $0.36 — Claude Haiku 5.5 is about 70% cheaper on this mix. Real workloads skew heavily toward input tokens, so weigh the input rate by your own ratio; the cached-input row above is the posted catalog rate for that model.
Switch between GPT-6.1 Terra and Claude Haiku 5.5
The API key and base URL stay the same, but this is not a one-string switch for every client or request. The model pages list GPT-6.1 Terra on /v1/responses and /v1/chat/completions, and Router One serves Claude Haiku 5.5 on /v1/messages and /v1/chat/completions, so Codex CLI (/v1/responses) runs only the GPT side and Claude Code (/v1/messages) only the Claude side. Per OpenAI's GPT-6 guide (checked 2026-10-28), GPT-6.1 Terra takes tool calls only on the Responses API and, at any reasoning effort other than none, no temperature, top_p or logprobs settings; per Anthropic's Claude Haiku 5.5 migration guide (checked 2026-10-10), Claude Haiku 5.5 returns a 400 for sampling settings it does not accept (omit temperature, top_p and top_k) and for an assistant prefill as the last turn. As of the 2026-10-28 plan response, both models are in no plan tier and bill the wallet per token.
curl https://api.router.one/v1/chat/completions \
-H "Authorization: Bearer sk-your-router-one-key" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-6.1-terra", "messages": [{"role": "user", "content": "Hello"}]}'
# Same request, other model — change one string:
# "model": "anthropic/claude-haiku-5.5"FAQ
Is GPT-6.1 Terra cheaper than Claude Haiku 5.5?
Compared at base-tier rates (GPT-6.1 Terra: request input ≤ 272,000 tokens; Claude Haiku 5.5: request input ≤ 100,000 tokens). Input: GPT-6.1 Terra $0.20 vs Claude Haiku 5.5 $0.06 / 1M tokens; Claude Haiku 5.5 has the lower rate. Output: GPT-6.1 Terra $1.00 vs Claude Haiku 5.5 $0.30 / 1M tokens; Claude Haiku 5.5 has the lower rate. Total cost depends on the workload's input, output and cache usage. GPT-6.1 Terra: request input ≤ 272,000 tokens: Input $0.20 / 1M tokens, Output $1.00 / 1M tokens, Cache write $0.25 / 1M tokens, Cached input $0.01 / 1M tokens; request input > 272,000 tokens: Input $0.40 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.02 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Claude Haiku 5.5: request input ≤ 100,000 tokens: Input $0.06 / 1M tokens, Output $0.30 / 1M tokens, Cache write $0.075 / 1M tokens, Cached input $0.006 / 1M tokens; request input > 100,000 tokens: Input $0.30 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.375 / 1M tokens, Cached input $0.03 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Rates change; the /models page is the live source of truth.
Is GPT-6.1 Terra or Claude Haiku 5.5 included in a Router One subscription?
Neither GPT-6.1 Terra nor Claude Haiku 5.5 is in a Router One plan, so every call to either bills the wallet per token.
Can I switch between GPT-6.1 Terra and Claude Haiku 5.5 without changing code?
The API key and base URL stay the same, but this is not a one-string switch for every client or request. The model pages list GPT-6.1 Terra on /v1/responses and /v1/chat/completions, and Router One serves Claude Haiku 5.5 on /v1/messages and /v1/chat/completions, so Codex CLI (/v1/responses) runs only the GPT side and Claude Code (/v1/messages) only the Claude side. Per OpenAI's GPT-6 guide (checked 2026-10-28), GPT-6.1 Terra takes tool calls only on the Responses API and, at any reasoning effort other than none, no temperature, top_p or logprobs settings; per Anthropic's Claude Haiku 5.5 migration guide (checked 2026-10-10), Claude Haiku 5.5 returns a 400 for sampling settings it does not accept (omit temperature, top_p and top_k) and for an assistant prefill as the last turn. As of the 2026-10-28 plan response, both models are in no plan tier and bill the wallet per token.
Where do these numbers come from?
Specs and prices on this page render from the live Router One catalog — the same data as the /models page — and refresh with it. Pricing methodology is documented on /pricing-methodology. Rates on this page were read from the live catalog on 2026-10-29 (UTC) and refresh within the hour.