anthropic/claude-haiku-4-5
estimated usage cost
$3.50
1,000 requests × (1,000 uncached input × $1.00 + 500 output × $5.00) / 1,000,000 = $3.50
base rates; no context pricing tiers are published.
Claude Haiku 4.5 vs Claude Opus 4.8
rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.
| specification | Claude Haiku 4.5 anthropic/claude-haiku-4-5 | Claude Opus 4.8 anthropic/claude-opus-4-8 |
|---|---|---|
| input · usd / 1m tok | $1.00 | $5.00 |
| output · usd / 1m tok | $5.00 | $25.00 |
| context window | 200ktokens | 1mtokens |
| modalities · in → out | takes text and image in, gives text out | takes text and image in, gives text out |
pricing
| base api rates · usd per 1m tokens | Claude Haiku 4.5 anthropic/claude-haiku-4-5 | Claude Opus 4.8 anthropic/claude-opus-4-8 |
|---|---|---|
| input | $1.00 | $5.00 |
| output | $5.00 | $25.00 |
| cache read | $0.10 | $0.50 |
| cache write · default ttl | $1.25 | $6.25 |
| cache write · 1h ttl | $2.00 | $10.00 |
the estimate below prices one workload at these rates on every model.
specifications
| as published | Claude Haiku 4.5 anthropic/claude-haiku-4-5 | Claude Opus 4.8 anthropic/claude-opus-4-8 |
|---|---|---|
| creator | Anthropic | Anthropic |
| model type | Text generation | Text generation |
| context window | 200,000tokens | 1,000,000tokens |
| input | takes text and image in, gives text out | takes text and image in, gives text out |
| output | text | text |
| tool calling | not verified | not verified |
| released | oct 15, 2025 | may 28, 2026 |
| endpoint | /v1/chat/completions | /v1/chat/completions |
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
benchmarks
| primary configuration | Claude Haiku 4.5 anthropic/claude-haiku-4-5 non-reasoning | Claude Opus 4.8 anthropic/claude-opus-4-8 max |
|---|---|---|
| intelligence index · gateway rank | 15.4#84 of 108 | 41.8#23 of 108 |
| omniscience | -7.6#45 of 84 | 28.8#6 of 84 |
| gpqa | 64.6%#72 of 80 | 92.0%#15 of 80 |
| humanity’s last exam | 4.2%#78 of 87 | 48.7%#7 of 87 |
| coding index | not measured | 74.3#15 of 64 |
| agentic index | not measured | 41.9#17 of 53 |
| mmmu-pro | 55.1% | not measured |
| livecodebench | 51.1% | not measured |
| aa-lcr | 49.7% | 77.7% |
| ifbench | 42.0% | 62.2% |
| aime 2025 | 39.0% | not measured |
| tau2 | 32.5% | 94.4% |
| terminal-bench hard | 27.3% | 58.3% |
| multilingual lcr | 4.4% | 45.6% |
| critpt | 0.0% | 20.9% |
| scicode | not measured | 54.4% |
| automationbench partial | not measured | 45.6% |
| analystagent | not measured | 45.0% |
| tau banking | not measured | 34.2% |
| gdp.pdf all-pass | not measured | 22.8% |
Claude Haiku 4.5 source ↗Claude Opus 4.8 source ↗
each column describes the tested configuration named under the model; performance and costs can differ on impossibl. a score one model was not measured on is left blank rather than scored zero. indices are ranked against every model on the gateway with one. last checked 2026-10-14.
estimate your cost
one token workload, priced on every model at the published rates, in usd. change the numbers to match yours.
anthropic/claude-opus-4-8
estimated usage cost
$17.50
1,000 requests × (1,000 uncached input × $5.00 + 500 output × $25.00) / 1,000,000 = $17.50
base rates; no context pricing tiers are published.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
summary
Claude Haiku 4.5 and Claude Opus 4.8 are available through the Impossibl API. they share the /v1/chat/completions endpoint; the model identifier selects the model for a request.
Claude Haiku 4.5 is created by Anthropic. It has a 200,000-token context window. Base API pricing (USD): $1.00 per million input tokens; $5.00 per million output tokens.
Claude Opus 4.8 is created by Anthropic. It has a 1,000,000-token context window. Base API pricing (USD): $5.00 per million input tokens; $25.00 per million output tokens.
Claude Haiku 4.5 →Claude Opus 4.8 →
this page compares Claude Haiku 4.5 vs Claude Opus 4.8 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.
view the source catalog ↗comparison as markdown ↗report a correction →